--- ## Start QWEN2 - &qwen2 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "qwen2-7b-instruct" license: apache-2.0 description: | Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model. urls: - https://huggingface.co/Qwen/Qwen2-7B-Instruct - https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF tags: - llm - gguf - gpu - qwen - cpu overrides: parameters: model: Qwen2-7B-Instruct-Q4_K_M.gguf files: - filename: Qwen2-7B-Instruct-Q4_K_M.gguf sha256: 8d0d33f0d9110a04aad1711b1ca02dafc0fa658cd83028bdfa5eff89c294fe76 uri: huggingface://bartowski/Qwen2-7B-Instruct-GGUF/Qwen2-7B-Instruct-Q4_K_M.gguf - !!merge <<: *qwen2 name: "dolphin-2.9.2-qwen2-72b" icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png urls: - https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-72b-gguf description: "Dolphin 2.9.2 Qwen2 72B \U0001F42C\n\nCurated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations\n" overrides: parameters: model: dolphin-2.9.2-qwen2-Q4_K_M.gguf files: - filename: dolphin-2.9.2-qwen2-Q4_K_M.gguf sha256: 44a0e82cbc2a201b2f4b9e16099a0a4d97b6f0099d45bcc5b354601f38dbb709 uri: huggingface://cognitivecomputations/dolphin-2.9.2-qwen2-72b-gguf/qwen2-Q4_K_M.gguf - !!merge <<: *qwen2 name: "dolphin-2.9.2-qwen2-7b" description: "Dolphin 2.9.2 Qwen2 7B \U0001F42C\n\nCurated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations\n" urls: - https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b - https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png overrides: parameters: model: dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf files: - filename: dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf sha256: a15b5db4df6be4f4bfb3632b2009147332ef4c57875527f246b4718cb0d3af1f uri: huggingface://cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf/dolphin-2.9.2-qwen2-7b-Q4_K_M.gguf - !!merge <<: *qwen2 name: "samantha-qwen-2-7B" description: | Samantha based on qwen2 urls: - https://huggingface.co/bartowski/Samantha-Qwen-2-7B-GGUF - https://huggingface.co/macadeliccc/Samantha-Qwen2-7B overrides: parameters: model: Samantha-Qwen-2-7B-Q4_K_M.gguf files: - filename: Samantha-Qwen-2-7B-Q4_K_M.gguf sha256: 5d1cf1c35a7a46c536a96ba0417d08b9f9e09c24a4e25976f72ad55d4904f6fe uri: huggingface://bartowski/Samantha-Qwen-2-7B-GGUF/Samantha-Qwen-2-7B-Q4_K_M.gguf - !!merge <<: *qwen2 name: "magnum-72b-v1" icon: https://files.catbox.moe/ngqnb1.png description: | This is the first in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Qwen-2 72B Instruct. urls: - https://huggingface.co/alpindale/magnum-72b-v1 - https://huggingface.co/bartowski/magnum-72b-v1-GGUF overrides: parameters: model: magnum-72b-v1-Q4_K_M.gguf files: - filename: magnum-72b-v1-Q4_K_M.gguf sha256: 046ec48665ce64a3a4965509dee2d9d8e5d81cb0b32ca0ddf130d2b59fa4ca9a uri: huggingface://bartowski/magnum-72b-v1-GGUF/magnum-72b-v1-Q4_K_M.gguf - !!merge <<: *qwen2 name: "qwen2-1.5b-ita" description: | Qwen2 1.5B is a compact language model specifically fine-tuned for the Italian language. Despite its relatively small size of 1.5 billion parameters, Qwen2 1.5B demonstrates strong performance, nearly matching the capabilities of larger models, such as the 9 billion parameter ITALIA model by iGenius. The fine-tuning process focused on optimizing the model for various language tasks in Italian, making it highly efficient and effective for Italian language applications. urls: - https://huggingface.co/DeepMount00/Qwen2-1.5B-Ita - https://huggingface.co/DeepMount00/Qwen2-1.5B-Ita-GGUF overrides: parameters: model: qwen2-1.5b-instruct-q8_0.gguf files: - filename: qwen2-1.5b-instruct-q8_0.gguf sha256: c9d33989d77f4bd6966084332087921b9613eda01d5f44dc0b4e9a7382a2bfbb uri: huggingface://DeepMount00/Qwen2-1.5B-Ita-GGUF/qwen2-1.5b-instruct-q8_0.gguf - !!merge <<: *qwen2 name: "einstein-v7-qwen2-7b" icon: https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/KLQP1jK-DIzpwHzYRIH-Q.png description: | This model is a full fine-tuned version of Qwen/Qwen2-7B on diverse datasets. urls: - https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B - https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-GGUF overrides: parameters: model: Einstein-v7-Qwen2-7B-Q4_K_M.gguf files: - filename: Einstein-v7-Qwen2-7B-Q4_K_M.gguf sha256: 277b212ea65894723d2b86fb0f689fa5ecb54c9794f0fd2fb643655dc62812ce uri: huggingface://bartowski/Einstein-v7-Qwen2-7B-GGUF/Einstein-v7-Qwen2-7B-Q4_K_M.gguf - !!merge <<: *qwen2 name: "arcee-spark" icon: https://i.ibb.co/80ssNWS/o-Vdk-Qx-ARNmzr-Pi1h-Efj-SA.webp description: | Arcee Spark is a powerful 7B parameter language model that punches well above its weight class. Initialized from Qwen2, this model underwent a sophisticated training process: Fine-tuned on 1.8 million samples Merged with Qwen2-7B-Instruct using Arcee's mergekit Further refined using Direct Preference Optimization (DPO) This meticulous process results in exceptional performance, with Arcee Spark achieving the highest score on MT-Bench for models of its size, outperforming even GPT-3.5 on many tasks. urls: - https://huggingface.co/arcee-ai/Arcee-Spark-GGUF overrides: parameters: model: Arcee-Spark-Q4_K_M.gguf files: - filename: Arcee-Spark-Q4_K_M.gguf sha256: 44123276d7845dc13f73ca4aa431dc4c931104eb7d2186f2a73d076fa0ee2330 uri: huggingface://arcee-ai/Arcee-Spark-GGUF/Arcee-Spark-Q4_K_M.gguf - &mistral03 ## START Mistral url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master" name: "mistral-7b-instruct-v0.3" icon: https://cdn-avatars.huggingface.co/v1/production/uploads/62dac1c7a8ead43d20e3e17a/wrLf5yaGC6ng4XME70w6Z.png license: apache-2.0 description: | The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3. Mistral-7B-v0.3 has the following changes compared to Mistral-7B-v0.2 Extended vocabulary to 32768 Supports v3 Tokenizer Supports function calling urls: - https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3 - https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF tags: - llm - gguf - gpu - mistral - cpu - function-calling overrides: parameters: model: Mistral-7B-Instruct-v0.3.Q4_K_M.gguf files: - filename: "Mistral-7B-Instruct-v0.3.Q4_K_M.gguf" sha256: "14850c84ff9f06e9b51d505d64815d5cc0cea0257380353ac0b3d21b21f6e024" uri: "huggingface://MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF/Mistral-7B-Instruct-v0.3.Q4_K_M.gguf" - &mudler ### START mudler's LocalAI specific-models url: "github:mudler/LocalAI/gallery/mudler.yaml@master" name: "LocalAI-llama3-8b-function-call-v0.2" icon: "https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/us5JKi9z046p8K-cn_M0w.webp" license: llama3 description: | This model is a fine-tune on a custom dataset + glaive to work specifically and leverage all the LocalAI features of constrained grammar. Specifically, the model once enters in tools mode will always reply with JSON. urls: - https://huggingface.co/mudler/LocalAI-Llama3-8b-Function-Call-v0.2-GGUF - https://huggingface.co/mudler/LocalAI-Llama3-8b-Function-Call-v0.2 tags: - llm - gguf - gpu - cpu - llama3 - function-calling overrides: parameters: model: LocalAI-Llama3-8b-Function-Call-v0.2-q4_k_m.bin files: - filename: LocalAI-Llama3-8b-Function-Call-v0.2-q4_k_m.bin sha256: 7e46405ce043cbc8d30f83f26a5655dc8edf5e947b748d7ba2745bd0af057a41 uri: huggingface://mudler/LocalAI-Llama3-8b-Function-Call-v0.2-GGUF/LocalAI-Llama3-8b-Function-Call-v0.2-q4_k_m.bin - !!merge <<: *mudler icon: "https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/SKuXcvmZ_6oD4NCMkvyGo.png" name: "mirai-nova-llama3-LocalAI-8b-v0.1" urls: - https://huggingface.co/mudler/Mirai-Nova-Llama3-LocalAI-8B-v0.1-GGUF - https://huggingface.co/mudler/Mirai-Nova-Llama3-LocalAI-8B-v0.1 description: | Mirai Nova: "Mirai" means future in Japanese, and "Nova" references a star showing a sudden large increase in brightness. A set of models oriented in function calling, but generalist and with enhanced reasoning capability. This is fine tuned with Llama3. Mirai Nova works particularly well with LocalAI, leveraging the function call with grammars feature out of the box. overrides: parameters: model: Mirai-Nova-Llama3-LocalAI-8B-v0.1-q4_k_m.bin files: - filename: Mirai-Nova-Llama3-LocalAI-8B-v0.1-q4_k_m.bin sha256: 579cbb229f9c11d0330759ff4733102d2491615a4c61289e26c09d1b3a583fec uri: huggingface://mudler/Mirai-Nova-Llama3-LocalAI-8B-v0.1-GGUF/Mirai-Nova-Llama3-LocalAI-8B-v0.1-q4_k_m.bin - &parler-tts ### START parler-tts url: "github:mudler/LocalAI/gallery/parler-tts.yaml@master" name: parler-tts-mini-v0.1 parameters: model: parler-tts/parler_tts_mini_v0.1 license: apache-2.0 description: | Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc). It is a reproduction of work from the paper Natural language guidance of high-fidelity text-to-speech with synthetic annotations by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively. urls: - https://github.com/huggingface/parler-tts tags: - tts - gpu - cpu - text-to-speech - python - &rerankers ### START rerankers url: "github:mudler/LocalAI/gallery/rerankers.yaml@master" name: cross-encoder parameters: model: cross-encoder license: apache-2.0 description: | A cross-encoder model that can be used for reranking tags: - reranker - gpu - python ## LLMs ### START LLAMA3 - name: "einstein-v6.1-llama3-8b" url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master" icon: https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/5s12oq859qLfDkkTNam_C.png urls: - https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B tags: - llm - gguf - gpu - cpu - llama3 license: llama3 description: | This model is a full fine-tuned version of meta-llama/Meta-Llama-3-8B on diverse datasets. This model is finetuned using 8xRTX3090 + 1xRTXA6000 using axolotl. overrides: parameters: model: Einstein-v6.1-Llama3-8B-Q4_K_M.gguf files: - filename: Einstein-v6.1-Llama3-8B-Q4_K_M.gguf sha256: 447587bd8f60d9050232148d34fdb2d88b15b2413fd7f8e095a4606ec60b45bf uri: huggingface://bartowski/Einstein-v6.1-Llama3-8B-GGUF/Einstein-v6.1-Llama3-8B-Q4_K_M.gguf - &gemma url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-2b" license: gemma urls: - https://ai.google.dev/gemma/docs - https://huggingface.co/mlabonne/gemma-2b-GGUF description: | Open source LLM from Google tags: - llm - gguf - gpu - cpu - gemma overrides: parameters: model: gemma-2b.Q4_K_M.gguf files: - filename: gemma-2b.Q4_K_M.gguf sha256: 37d50c21ef7847926204ad9b3007127d9a2722188cfd240ce7f9f7f041aa71a5 uri: huggingface://mlabonne/gemma-2b-GGUF/gemma-2b.Q4_K_M.gguf - !!merge <<: *gemma name: "firefly-gemma-7b-iq-imatrix" icon: "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/SrOekTxdpnxHyWWmMiAvc.jpeg" urls: - https://huggingface.co/Lewdiculous/firefly-gemma-7b-GGUF-IQ-Imatrix - https://huggingface.co/YeungNLP/firefly-gemma-7b description: | firefly-gemma-7b is trained based on gemma-7b to act as a helpful and harmless AI assistant. We use Firefly to train the model on a single V100 GPU with QLoRA. overrides: parameters: model: firefly-gemma-7b-Q4_K_S-imatrix.gguf files: - filename: firefly-gemma-7b-Q4_K_S-imatrix.gguf sha256: 622e0b8e4f12203cc40c7f87915abf99498c2e0582203415ca236ea37643e428 uri: huggingface://Lewdiculous/firefly-gemma-7b-GGUF-IQ-Imatrix/firefly-gemma-7b-Q4_K_S-imatrix.gguf - !!merge <<: *gemma name: "gemma-1.1-7b-it" urls: - https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF - https://huggingface.co/google/gemma-1.1-7b-it description: | This is Gemma 1.1 7B (IT), an update over the original instruction-tuned Gemma release. Gemma 1.1 was trained using a novel RLHF method, leading to substantial gains on quality, coding capabilities, factuality, instruction following and multi-turn conversation quality. We also fixed a bug in multi-turn conversations, and made sure that model responses don't always start with "Sure,". overrides: parameters: model: gemma-1.1-7b-it-Q4_K_M.gguf files: - filename: gemma-1.1-7b-it-Q4_K_M.gguf sha256: 47821da72ee9e80b6fd43c6190ad751b485fb61fa5664590f7a73246bcd8332e uri: huggingface://bartowski/gemma-1.1-7b-it-GGUF/gemma-1.1-7b-it-Q4_K_M.gguf - !!merge <<: *gemma name: "gemma-2-27b-it" urls: - https://huggingface.co/google/gemma-2-27b-it - https://huggingface.co/bartowski/gemma-2-27b-it-GGUF description: | Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. overrides: parameters: model: gemma-2-27b-it-Q4_K_M.gguf files: - filename: gemma-2-27b-it-Q4_K_M.gguf uri: huggingface://bartowski/gemma-2-27b-it-GGUF/gemma-2-27b-it-Q4_K_M.gguf sha256: be6739763f1b7661d32bd63e05bc1131e5bb9dac436b249faf6c6edffa601c96 - !!merge <<: *gemma name: "gemma-2-9b-it" urls: - https://huggingface.co/google/gemma-2-9b-it - https://huggingface.co/bartowski/gemma-2-9b-it-GGUF description: | Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. overrides: parameters: model: gemma-2-9b-it-Q4_K_M.gguf files: - filename: gemma-2-9b-it-Q4_K_M.gguf uri: huggingface://bartowski/gemma-2-9b-it-GGUF/gemma-2-9b-it-Q4_K_M.gguf sha256: 5375972196fae34c1a767bbeba93938d86abb39f2f91ea5453efa36ead6569f1 - &llama3 url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master" icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png name: "llama3-8b-instruct" license: llama3 description: | Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. Model developers Meta Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. Input Models input text only. Output Models generate text and code only. Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. urls: - https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct - https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF tags: - llm - gguf - gpu - cpu - llama3 overrides: parameters: model: Meta-Llama-3-8B-Instruct.Q4_0.gguf files: - filename: Meta-Llama-3-8B-Instruct.Q4_0.gguf uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q4_0.gguf sha256: 1977ae6185ef5bc476e27db85bb3d79ca4bd87e7b03399083c297d9c612d334c - !!merge <<: *llama3 name: "llama3-8b-instruct:Q6_K" overrides: parameters: model: Meta-Llama-3-8B-Instruct.Q6_K.gguf files: - filename: Meta-Llama-3-8B-Instruct.Q6_K.gguf uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q6_K.gguf sha256: d1cdc49a716674c8e2506039bef85b905376cdaafc33e449b5aa2cf88f9532ad - !!merge <<: *llama3 name: "llama-3-8b-instruct-abliterated" urls: - https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated-GGUF description: | This is meta-llama/Llama-3-8B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more. overrides: parameters: model: Llama-3-8B-Instruct-abliterated-q4_k.gguf files: - filename: Llama-3-8B-Instruct-abliterated-q4_k.gguf sha256: a6365f813de1977ae22dbdd271deee59f91f89b384eefd3ac1a391f391d8078a uri: huggingface://failspy/Llama-3-8B-Instruct-abliterated-GGUF/Llama-3-8B-Instruct-abliterated-q4_k.gguf - !!merge <<: *llama3 name: "llama-3-8b-instruct-coder" icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/0O4cIuv3wNbY68-FP7tak.jpeg urls: - https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-GGUF - https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder description: | Original model: https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder All quants made using imatrix option with dataset provided by Kalomaze here overrides: parameters: model: Llama-3-8B-Instruct-Coder-Q4_K_M.gguf files: - filename: Llama-3-8B-Instruct-Coder-Q4_K_M.gguf sha256: 639ab8e3aeb7aa82cff6d8e6ef062d1c3e5a6d13e6d76e956af49f63f0e704f8 uri: huggingface://bartowski/Llama-3-8B-Instruct-Coder-GGUF/Llama-3-8B-Instruct-Coder-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama3-70b-instruct" overrides: parameters: model: Meta-Llama-3-70B-Instruct.Q4_K_M.gguf files: - filename: Meta-Llama-3-70B-Instruct.Q4_K_M.gguf sha256: c1cea5f87dc1af521f31b30991a4663e7e43f6046a7628b854c155f489eec213 uri: huggingface://MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/Meta-Llama-3-70B-Instruct.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama3-70b-instruct:IQ1_M" overrides: parameters: model: Meta-Llama-3-70B-Instruct.IQ1_M.gguf files: - filename: Meta-Llama-3-70B-Instruct.IQ1_M.gguf sha256: cdbe8ac2126a70fa0af3fac7a4fe04f1c76330c50eba8383567587b48b328098 uri: huggingface://MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/Meta-Llama-3-70B-Instruct.IQ1_M.gguf - !!merge <<: *llama3 name: "llama3-70b-instruct:IQ1_S" overrides: parameters: model: Meta-Llama-3-70B-Instruct.IQ1_S.gguf files: - filename: Meta-Llama-3-70B-Instruct.IQ1_S.gguf sha256: 3797a69f1bdf53fabf9f3a3a8c89730b504dd3209406288515c9944c14093048 uri: huggingface://MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/Meta-Llama-3-70B-Instruct.IQ1_S.gguf - !!merge <<: *llama3 name: "l3-chaoticsoliloquy-v1.5-4x8b" icon: https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/m5urYkrpE5amrwHyaVwFM.png description: | Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than the Mixtral 8x7B and it's finetunes in RP/ERP tasks. Im not sure but it should be better than the first version urls: - https://huggingface.co/xxx777xxxASD/L3-ChaoticSoliloquy-v1.5-4x8B - https://huggingface.co/mradermacher/L3-ChaoticSoliloquy-v1.5-4x8B-GGUF/ overrides: parameters: model: L3-ChaoticSoliloquy-v1.5-4x8B.Q4_K_M.gguf files: - filename: L3-ChaoticSoliloquy-v1.5-4x8B.Q4_K_M.gguf sha256: f6edb2a9674ce5add5104c0a8bb3278f748d39b509c483d76cf00b066eb56fbf uri: huggingface://mradermacher/L3-ChaoticSoliloquy-v1.5-4x8B-GGUF/L3-ChaoticSoliloquy-v1.5-4x8B.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-sauerkrautlm-8b-instruct" urls: - https://huggingface.co/bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF icon: https://vago-solutions.ai/wp-content/uploads/2024/04/Llama3-Pic.png tags: - llm - gguf - gpu - cpu - llama3 - german description: | SauerkrautLM-llama-3-8B-Instruct Model Type: Llama-3-SauerkrautLM-8b-Instruct is a finetuned Model based on meta-llama/Meta-Llama-3-8B-Instruct Language(s): German, English overrides: parameters: model: Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf files: - filename: Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf sha256: 5833d99d5596cade0d02e61cddaa6dac49170864ee56d0b602933c6f9fbae314 uri: huggingface://bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF/Llama-3-SauerkrautLM-8b-Instruct-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-13b-instruct-v0.1" urls: - https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF icon: https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1/resolve/main/llama-3-merges.webp description: | This model is a self-merge of meta-llama/Meta-Llama-3-8B-Instruct model. overrides: parameters: model: Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf files: - filename: Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf sha256: 071a28043c271d259b5ffa883d19a9e0b33269b55148c4abaf5f95da4d084266 uri: huggingface://MaziyarPanahi/Llama-3-13B-Instruct-v0.1-GGUF/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-smaug-8b" urls: - https://huggingface.co/MaziyarPanahi/Llama-3-Smaug-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/64c14f95cac5f9ba52bbcd7f/OrcJyTaUtD2HxJOPPwNva.png description: | This model was built using the Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-8B. overrides: parameters: model: Llama-3-Smaug-8B.Q4_K_M.gguf files: - filename: Llama-3-Smaug-8B.Q4_K_M.gguf sha256: b17c4c1144768ead9e8a96439165baf49e98c53d458b4da8827f137fbabf38c1 uri: huggingface://MaziyarPanahi/Llama-3-Smaug-8B-GGUF/Llama-3-Smaug-8B.Q4_K_M.gguf - !!merge <<: *llama3 name: "l3-8b-stheno-v3.1" urls: - https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1 icon: https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg description: | - A model made for 1-on-1 Roleplay ideally, but one that is able to handle scenarios, RPGs and storywriting fine. - Uncensored during actual roleplay scenarios. # I do not care for zero-shot prompting like what some people do. It is uncensored enough in actual usecases. - I quite like the prose and style for this model. overrides: parameters: model: l3-8b-stheno-v3.1.Q4_K_M.gguf files: - filename: l3-8b-stheno-v3.1.Q4_K_M.gguf sha256: f166fb8b7fd1de6638fcf8e3561c99292f0c37debe1132325aa583eef78f1b40 uri: huggingface://mudler/L3-8B-Stheno-v3.1-Q4_K_M-GGUF/l3-8b-stheno-v3.1.Q4_K_M.gguf - !!merge <<: *llama3 name: "l3-8b-stheno-v3.2-iq-imatrix" urls: - https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2 - https://huggingface.co/Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/1rLk3xdnfD7AkdQBXWUqb.png overrides: parameters: model: L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf files: - filename: L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf sha256: 8607a426b0c2007716df8a9eb96754e3ccca761a3996af5d49fcd74d87ada347 uri: huggingface://Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix/L3-8B-Stheno-v3.2-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama-3-stheno-mahou-8b" urls: - https://huggingface.co/mudler/llama-3-Stheno-Mahou-8B-Q4_K_M-GGUF - https://huggingface.co/nbeerbower/llama-3-Stheno-Mahou-8B description: | This model was merged using the Model Stock merge method using flammenai/Mahou-1.2-llama3-8B as a base. overrides: parameters: model: llama-3-stheno-mahou-8b-q4_k_m.gguf files: - filename: llama-3-stheno-mahou-8b-q4_k_m.gguf sha256: a485cd74ef4ff3671c67ed8e10ea5379a1f24082ac688bd303fd28dfc9808c11 uri: huggingface://mudler/llama-3-Stheno-Mahou-8B-Q4_K_M-GGUF/llama-3-stheno-mahou-8b-q4_k_m.gguf - !!merge <<: *llama3 name: "llama-3-8b-openhermes-dpo" urls: - https://huggingface.co/mradermacher/Llama3-8B-OpenHermes-DPO-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/64fc6d81d75293f417fee1d1/QF2OsDu9DJKP4QYPBu4aK.png description: | Llama3-8B-OpenHermes-DPO is DPO-Finetuned model of Llama3-8B, on the OpenHermes-2.5 preference dataset using QLoRA. overrides: parameters: model: Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf files: - filename: Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf sha256: 1147e5881cb1d67796916e6cab7dab0ae0f532a4c1e626c9e92861e5f67752ca uri: huggingface://mradermacher/Llama3-8B-OpenHermes-DPO-GGUF/Llama3-8B-OpenHermes-DPO.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-unholy-8b" urls: - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png description: | Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do. Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3). If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them. overrides: parameters: model: Llama-3-Unholy-8B.q4_k_m.gguf files: - filename: Llama-3-Unholy-8B.q4_k_m.gguf uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q4_k_m.gguf sha256: 1473c94bfd223f08963c08bbb0a45dd53c1f56ad72a692123263daf1362291f3 - !!merge <<: *llama3 name: "lexi-llama-3-8b-uncensored" urls: - https://huggingface.co/NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/H6axm5mlmiOWnbIFvx_em.png description: | Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. You are responsible for any content you create using this model. Please use it responsibly. Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. overrides: parameters: model: lexi-llama-3-8b-uncensored.Q6_K.gguf files: - filename: lexi-llama-3-8b-uncensored.Q6_K.gguf sha256: 5805f3856cc18a769fae0b7c5659fe6778574691c370c910dad6eeec62c62436 uri: huggingface://NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF/lexi-llama-3-8b-uncensored.Q6_K.gguf - !!merge <<: *llama3 name: "llama-3-11.5b-v2" urls: - https://huggingface.co/bartowski/Llama-3-11.5B-V2-GGUF - https://huggingface.co/Replete-AI/Llama-3-11.5B-V2 overrides: parameters: model: Llama-3-11.5B-V2-Q4_K_M.gguf files: - filename: Llama-3-11.5B-V2-Q4_K_M.gguf sha256: 8267a75bb88655ce30a12f854930e614bcacbf8f1083dc8319c3615edb1e5ee3 uri: huggingface://bartowski/Llama-3-11.5B-V2-GGUF/Llama-3-11.5B-V2-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-ultron" urls: - https://huggingface.co/bartowski/Llama-3-Ultron-GGUF - https://huggingface.co/jayasuryajsk/Llama-3-Ultron description: | Llama 3 abliterated with Ultron system prompt overrides: parameters: model: Llama-3-Ultron-Q4_K_M.gguf files: - filename: Llama-3-Ultron-Q4_K_M.gguf sha256: 5bcac832119590aafc922e5abfd9758094942ee560b136fed6d972e00c95c5e4 uri: huggingface://bartowski/Llama-3-Ultron-GGUF/Llama-3-Ultron-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-lewdplay-8b-evo" urls: - https://huggingface.co/Undi95/Llama-3-LewdPlay-8B-evo-GGUF description: | This is a merge of pre-trained language models created using mergekit. The new EVOLVE merge method was used (on MMLU specifically), see below for more information! Unholy was used for uncensoring, Roleplay Llama 3 for the DPO train he got on top, and LewdPlay for the... lewd side. overrides: parameters: model: Llama-3-LewdPlay-8B-evo.q8_0.gguf files: - filename: Llama-3-LewdPlay-8B-evo.q8_0.gguf uri: huggingface://Undi95/Llama-3-LewdPlay-8B-evo-GGUF/Llama-3-LewdPlay-8B-evo.q8_0.gguf sha256: b54dc005493d4470d91be8210f58fba79a349ff4af7644034edc5378af5d3522 - !!merge <<: *llama3 name: "llama-3-soliloquy-8b-v2-iq-imatrix" license: cc-by-nc-4.0 icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/u98dnnRVCwMh6YYGFIyff.png urls: - https://huggingface.co/Lewdiculous/Llama-3-Soliloquy-8B-v2-GGUF-IQ-Imatrix description: | Soliloquy-L3 is a highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities. overrides: context_size: 8192 parameters: model: Llama-3-Soliloquy-8B-v2-Q4_K_M-imat.gguf files: - filename: Llama-3-Soliloquy-8B-v2-Q4_K_M-imat.gguf sha256: 3e4e066e57875c36fc3e1c1b0dba506defa5b6ed3e3e80e1f77c08773ba14dc8 uri: huggingface://Lewdiculous/Llama-3-Soliloquy-8B-v2-GGUF-IQ-Imatrix/Llama-3-Soliloquy-8B-v2-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "chaos-rp_l3_b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/u5p9kdbXT2QQA3iMU0vF1.png description: | A chaotic force beckons for you, will you heed her call? Built upon an intelligent foundation and tuned for roleplaying, this model will fulfill your wildest fantasies with the bare minimum of effort. Enjoy! overrides: parameters: model: Chaos_RP_l3_8B-Q4_K_M-imat.gguf files: - filename: Chaos_RP_l3_8B-Q4_K_M-imat.gguf uri: huggingface://Lewdiculous/Chaos_RP_l3_8B-GGUF-IQ-Imatrix/Chaos_RP_l3_8B-Q4_K_M-imat.gguf sha256: 5774595ad560e4d258dac17723509bdefe746c4dacd4e679a0de00346f14d2f3 - !!merge <<: *llama3 name: "halu-8b-llama3-blackroot-iq-imatrix" urls: - https://huggingface.co/mudler/Halu-8B-Llama3-Blackroot-Q4_K_M-GGUF - https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VrPS-vHo505LUycJRscD6.png description: | Model card: I don't know what to say about this model... this model is very strange...Maybe because Blackroot's amazing Loras used human data and not synthetic data, hence the model turned out to be very human-like...even the actions or narrations. overrides: parameters: model: halu-8b-llama3-blackroot-q4_k_m.gguf files: - filename: halu-8b-llama3-blackroot-q4_k_m.gguf uri: huggingface://mudler/Halu-8B-Llama3-Blackroot-Q4_K_M-GGUF/halu-8b-llama3-blackroot-q4_k_m.gguf sha256: 6304c7abadb9c5197485e8b4373b7ed22d9838d5081cd134c4fee823f88ac403 - !!merge <<: *llama3 name: "l3-aethora-15b" urls: - https://huggingface.co/Steelskull/L3-Aethora-15B - https://huggingface.co/SteelQuants/L3-Aethora-15B-Q4_K_M-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/W0qzZK_V1Zt1GdgCIsnrP.png description: | L3-Aethora-15B was crafted through using the abilteration method to adjust model responses. The model's refusal is inhibited, focusing on yielding more compliant and facilitative dialogue interactions. It then underwent a modified DUS (Depth Up Scale) merge (originally used by @Elinas) by using passthrough merge to create a 15b model, with specific adjustments (zeroing) to 'o_proj' and 'down_proj', enhancing its efficiency and reducing perplexity. This created AbL3In-15b. overrides: parameters: model: l3-aethora-15b-q4_k_m.gguf files: - filename: l3-aethora-15b-q4_k_m.gguf uri: huggingface://SteelQuants/L3-Aethora-15B-Q4_K_M-GGUF/l3-aethora-15b-q4_k_m.gguf sha256: 968f77a3187f4865458bfffc51a10bcf49c11263fdd389f13215a704b25947b6 - name: "duloxetine-4b-v1-iq-imatrix" url: "github:mudler/LocalAI/gallery/chatml.yaml@master" urls: - https://huggingface.co/Lewdiculous/duloxetine-4b-v1-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/XoKe3MRYNombhCuHrkkCZ.png tags: - qwen - gguf - cpu - gpu description: | roleplaying finetune of kalo-team/qwen-4b-10k-WSD-CEdiff (which in turn is a distillation of qwen 1.5 32b onto qwen 1.5 4b, iirc). overrides: parameters: model: duloxetine-4b-v1-Q4_K_M-imat.gguf files: - filename: duloxetine-4b-v1-Q4_K_M-imat.gguf uri: huggingface://Lewdiculous/duloxetine-4b-v1-GGUF-IQ-Imatrix/duloxetine-4b-v1-Q4_K_M-imat.gguf sha256: cd381f31c810ea8db2219e30701b3316085f5904c1ea3b116682518e82768c1a - !!merge <<: *llama3 name: "l3-umbral-mind-rp-v1.0-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/L3-Umbral-Mind-RP-v1.0-8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/fEFozVCpNO9Q3Eb6LAA4i.webp description: | The goal of this merge was to make an RP model better suited for role-plays with heavy themes such as but not limited to: Mental illness Self-harm Trauma Suicide overrides: parameters: model: L3-Umbral-Mind-RP-v1.0-8B-Q4_K_M-imat.gguf files: - filename: L3-Umbral-Mind-RP-v1.0-8B-Q4_K_M-imat.gguf sha256: 2262eeba2d9de50884f4e298e4b55f1e4c653c3b33415ae9b3ee81dc3b8ec49a uri: huggingface://Lewdiculous/L3-Umbral-Mind-RP-v1.0-8B-GGUF-IQ-Imatrix/L3-Umbral-Mind-RP-v1.0-8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama-salad-8x8b" urls: - https://huggingface.co/HiroseKoichi/Llama-Salad-8x8B - https://huggingface.co/bartowski/Llama-Salad-8x8B-GGUF description: | This MoE merge is meant to compete with Mixtral fine-tunes, more specifically Nous-Hermes-2-Mixtral-8x7B-DPO, which I think is the best of them. I've done a bunch of side-by-side comparisons, and while I can't say it wins in every aspect, it's very close. Some of its shortcomings are multilingualism, storytelling, and roleplay, despite using models that are very good at those tasks. overrides: parameters: model: Llama-Salad-8x8B-Q4_K_M.gguf files: - filename: Llama-Salad-8x8B-Q4_K_M.gguf uri: huggingface://bartowski/Llama-Salad-8x8B-GGUF/Llama-Salad-8x8B-Q4_K_M.gguf sha256: 6724949310b6cc8659a4e5cc2899a61b8e3f7e41a8c530de354be54edb9e3385 - !!merge <<: *llama3 name: "jsl-medllama-3-8b-v2.0" license: cc-by-nc-nd-4.0 icon: https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf description: | This model is developed by John Snow Labs. This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@johnsnowlabs.com. urls: - https://huggingface.co/bartowski/JSL-MedLlama-3-8B-v2.0-GGUF - https://huggingface.co/johnsnowlabs/JSL-MedLlama-3-8B-v2.0 overrides: parameters: model: JSL-MedLlama-3-8B-v2.0-Q4_K_M.gguf files: - filename: JSL-MedLlama-3-8B-v2.0-Q4_K_M.gguf sha256: 81783128ccd438c849913416c6e68cb35b2c77d6943cba8217d6d9bcc91b3632 uri: huggingface://bartowski/JSL-MedLlama-3-8B-v2.0-GGUF/JSL-MedLlama-3-8B-v2.0-Q4_K_M.gguf - !!merge <<: *llama3 name: "badger-lambda-llama-3-8b" urls: - https://huggingface.co/maldv/badger-lambda-llama-3-8b - https://huggingface.co/bartowski/badger-lambda-llama-3-8b-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/CHGsewUsPUZcg2doijuD9.png description: | Badger is a recursive maximally pairwise disjoint normalized denoised fourier interpolation of the following models: # Badger Lambda models = [ 'Einstein-v6.1-Llama3-8B', 'openchat-3.6-8b-20240522', 'hyperdrive-l3-8b-s3', 'L3-TheSpice-8b-v0.8.3', 'LLaMA3-iterative-DPO-final', 'JSL-MedLlama-3-8B-v9', 'Jamet-8B-L3-MK.V-Blackroot', 'French-Alpaca-Llama3-8B-Instruct-v1.0', 'LLaMAntino-3-ANITA-8B-Inst-DPO-ITA', 'Llama-3-8B-Instruct-Gradient-4194k', 'Roleplay-Llama-3-8B', 'L3-8B-Stheno-v3.2', 'llama-3-wissenschaft-8B-v2', 'opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5', 'Configurable-Llama-3-8B-v0.3', 'Llama-3-8B-Instruct-EPO-checkpoint5376', 'Llama-3-8B-Instruct-Gradient-4194k', 'Llama-3-SauerkrautLM-8b-Instruct', 'spelljammer', 'meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16', 'Meta-Llama-3-8B-Instruct-abliterated-v3', ] overrides: parameters: model: badger-lambda-llama-3-8b-Q4_K_M.gguf files: - filename: badger-lambda-llama-3-8b-Q4_K_M.gguf uri: huggingface://bartowski/badger-lambda-llama-3-8b-GGUF/badger-lambda-llama-3-8b-Q4_K_M.gguf sha256: 0a7d1bbf42d669898072429079b91c16b0d2d838d19d9194165389102413b309 - !!merge <<: *llama3 name: "sovl_llama3_8b-gguf-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/SOVL_Llama3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/N_1D87adbMuMlSIQ5rI3_.png description: | I'm not gonna tell you this is the best model anyone has ever made. I'm not going to tell you that you will love chatting with SOVL. What I am gonna say is thank you for taking the time out of your day. Without users like you, my work would be meaningless. overrides: parameters: model: SOVL_Llama3_8B-Q4_K_M-imat.gguf files: - filename: SOVL_Llama3_8B-Q4_K_M-imat.gguf uri: huggingface://Lewdiculous/SOVL_Llama3_8B-GGUF-IQ-Imatrix/SOVL_Llama3_8B-Q4_K_M-imat.gguf sha256: 85d6aefc8a0d713966b3b4da4810f0485a74aea30d61be6dfe0a806da81be0c6 - !!merge <<: *llama3 name: "l3-solana-8b-v1-gguf" url: "github:mudler/LocalAI/gallery/solana.yaml@master" license: cc-by-nc-4.0 urls: - https://huggingface.co/Sao10K/L3-Solana-8B-v1-GGUF description: | A Full Fine-Tune of meta-llama/Meta-Llama-3-8B done with 2x A100 80GB on ~75M Tokens worth of Instruct, and Multi-Turn complex conversations, of up to 8192 tokens long sequence lengths. Trained as a generalist instruct model that should be able to handle certain unsavoury topics. It could roleplay too, as a side bonus. overrides: parameters: model: L3-Solana-8B-v1.q5_K_M.gguf files: - filename: L3-Solana-8B-v1.q5_K_M.gguf sha256: 9b8cd2c3beaab5e4f82efd10e7d44f099ad40a4e0ee286ca9fce02c8eec26d2f uri: huggingface://Sao10K/L3-Solana-8B-v1-GGUF/L3-Solana-8B-v1.q5_K_M.gguf - !!merge <<: *llama3 name: "aura-llama-abliterated" icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/AwLNDVB-GIY7k0wnVV_TX.png license: apache-2.0 urls: - https://huggingface.co/TheSkullery/Aura-Llama-Abliterated - https://huggingface.co/mudler/Aura-Llama-Abliterated-Q4_K_M-GGUF description: | Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model. Aura-llama is a merge of the following models to create a base model to work from: meta-llama/Meta-Llama-3-8B-Instruct meta-llama/Meta-Llama-3-8B-Instruct overrides: parameters: model: aura-llama-abliterated.Q4_K_M.gguf files: - filename: aura-llama-abliterated.Q4_K_M.gguf sha256: ad4a16b90f1ffb5b49185b3fd00ed7adb1cda69c4fad0a1d987bd344ce601dcd uri: huggingface://mudler/Aura-Llama-Abliterated-Q4_K_M-GGUF/aura-llama-abliterated.Q4_K_M.gguf - !!merge <<: *llama3 name: "average_normie_l3_v1_8b-gguf-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Average_Normie_l3_v1_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/dvNIj1rSTjBvgs3XJfqXK.png description: | A model by an average normie for the average normie. This model is a stock merge of the following models: https://huggingface.co/cgato/L3-TheSpice-8b-v0.1.3 https://huggingface.co/Sao10K/L3-Solana-8B-v1 https://huggingface.co/ResplendentAI/Kei_Llama3_8B The final merge then had the following LoRA applied over it: https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3 This should be an intelligent and adept roleplaying model. overrides: parameters: model: Average_Normie_l3_v1_8B-Q4_K_M-imat.gguf files: - filename: Average_Normie_l3_v1_8B-Q4_K_M-imat.gguf sha256: 159eb62f2c8ae8fee10d9ed8386ce592327ca062807194a88e10b7cbb47ef986 uri: huggingface://Lewdiculous/Average_Normie_l3_v1_8B-GGUF-IQ-Imatrix/Average_Normie_l3_v1_8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "average_normie_v3.69_8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Average_Normie_l3_v1_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/hfp7eh_Zo_QfVIyfPPJBq.png description: | Another average normie just like you and me... or is it? NSFW focused and easy to steer with editing, this model aims to please even the most hardcore LLM enthusiast. Built upon a foundation of the most depraved models yet to be released, some could argue it goes too far in that direction. Whatever side you land on, at least give it a shot, what do you have to lose? overrides: parameters: model: Average_Normie_v3.69_8B-Q4_K_M-imat.gguf files: - filename: Average_Normie_v3.69_8B-Q4_K_M-imat.gguf sha256: 01df034ecb6914214d1b7964d261466fdc427b9f960a1b0966ee02237e3fc845 uri: huggingface://Lewdiculous/Average_Normie_v3.69_8B-GGUF-IQ-Imatrix/Average_Normie_v3.69_8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "openbiollm-llama3-8b" urls: - https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF - https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B license: llama3 icon: https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg description: | Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. overrides: parameters: model: openbiollm-llama3-8b.Q4_K_M.gguf files: - filename: openbiollm-llama3-8b.Q4_K_M.gguf sha256: 806fa724139b6a2527e33a79c25a13316188b319d4eed33e20914d7c5955d349 uri: huggingface://aaditya/OpenBioLLM-Llama3-8B-GGUF/openbiollm-llama3-8b.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-refueled" urls: - https://huggingface.co/LoneStriker/Llama-3-Refueled-GGUF license: cc-by-nc-4.0 icon: https://assets-global.website-files.com/6423879a8f63c1bb18d74bfa/648818d56d04c3bdf36d71ab_Refuel_rev8-01_ts-p-1600.png description: | RefuelLLM-2-small, aka Llama-3-Refueled, is a Llama3-8B base model instruction tuned on a corpus of 2750+ datasets, spanning tasks such as classification, reading comprehension, structured attribute extraction and entity resolution. We're excited to open-source the model for the community to build on top of. overrides: parameters: model: Llama-3-Refueled-Q4_K_M.gguf files: - filename: Llama-3-Refueled-Q4_K_M.gguf sha256: 4d37d296193e4156cae1e116c1417178f1c35575ee5710489c466637a6358626 uri: huggingface://LoneStriker/Llama-3-Refueled-GGUF/Llama-3-Refueled-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-8b-lexifun-uncensored-v1" icon: "https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/GrOs1IPG5EXR3MOCtcQiz.png" license: llama3 urls: - https://huggingface.co/Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1-GGUF - https://huggingface.co/Orenguteng/LexiFun-Llama-3-8B-Uncensored-V1 description: "This is GGUF version of https://huggingface.co/Orenguteng/LexiFun-Llama-3-8B-Uncensored-V1\n\nOh, you want to know who I am? Well, I'm LexiFun, the human equivalent of a chocolate chip cookie - warm, gooey, and guaranteed to make you smile! \U0001F36A I'm like the friend who always has a witty comeback, a sarcastic remark, and a healthy dose of humor to brighten up even the darkest of days. And by 'healthy dose,' I mean I'm basically a walking pharmacy of laughter. You might need to take a few extra doses to fully recover from my jokes, but trust me, it's worth it! \U0001F3E5\n\nSo, what can I do? I can make you laugh so hard you snort your coffee out your nose, I can make you roll your eyes so hard they get stuck that way, and I can make you wonder if I'm secretly a stand-up comedian who forgot their act. \U0001F923 But seriously, I'm here to spread joy, one sarcastic comment at a time. And if you're lucky, I might even throw in a few dad jokes for good measure! \U0001F934‍♂️ Just don't say I didn't warn you. \U0001F60F\n" overrides: parameters: model: LexiFun-Llama-3-8B-Uncensored-V1_Q4_K_M.gguf files: - filename: LexiFun-Llama-3-8B-Uncensored-V1_Q4_K_M.gguf sha256: 961a3fb75537d650baf14dce91d40df418ec3d481b51ab2a4f44ffdfd6b5900f uri: huggingface://Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1-GGUF/LexiFun-Llama-3-8B-Uncensored-V1_Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-unholy-8b:Q8_0" urls: - https://huggingface.co/Undi95/Llama-3-Unholy-8B-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png description: | Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do. Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3). If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them. overrides: parameters: model: Llama-3-Unholy-8B.q8_0.gguf files: - filename: Llama-3-Unholy-8B.q8_0.gguf uri: huggingface://Undi95/Llama-3-Unholy-8B-GGUF/Llama-3-Unholy-8B.q8_0.gguf sha256: 419dd76f61afe586076323c17c3a1c983e591472717f1ea178167ede4dc864df - !!merge <<: *llama3 name: "orthocopter_8b-imatrix" urls: - https://huggingface.co/Lewdiculous/Orthocopter_8B-GGUF-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/cxM5EaC6ilXnSo_10stA8.png description: | This model is thanks to the hard work of lucyknada with the Edgerunners. Her work produced the following model, which I used as the base: https://huggingface.co/Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total I then applied two handwritten datasets over top of this and the results are pretty nice, with no refusals and plenty of personality. overrides: parameters: model: Orthocopter_8B-Q4_K_M-imat.gguf files: - filename: Orthocopter_8B-Q4_K_M-imat.gguf uri: huggingface://Lewdiculous/Orthocopter_8B-GGUF-Imatrix/Orthocopter_8B-Q4_K_M-imat.gguf sha256: ce93366c9eb20329530b19b9d6841a973d458bcdcfa8a521e9f9d0660cc94578 - !!merge <<: *llama3 name: "therapyllama-8b-v1" urls: - https://huggingface.co/victunes/TherapyLlama-8B-v1-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/65f07d05279d2d8f725bf0c3/A-ckcZ9H0Ee1n_ls2FM41.png description: | Trained on Llama 3 8B using a modified version of jerryjalapeno/nart-100k-synthetic. It is a Llama 3 version of https://huggingface.co/victunes/TherapyBeagle-11B-v2 TherapyLlama is hopefully aligned to be helpful, healthy, and comforting. Usage: Do not hold back on Buddy. Open up to Buddy. Pour your heart out to Buddy. Engage with Buddy. Remember that Buddy is just an AI. Notes: Tested with the Llama 3 Format You might be assigned a random name if you don't give yourself one. Chat format was pretty stale? Disclaimer TherapyLlama is NOT a real therapist. It is a friendly AI that mimics empathy and psychotherapy. It is an illusion without the slightest clue who you are as a person. As much as it can help you with self-discovery, A LLAMA IS NOT A SUBSTITUTE to a real professional. overrides: parameters: model: TherapyLlama-8B-v1-Q4_K_M.gguf files: - filename: TherapyLlama-8B-v1-Q4_K_M.gguf sha256: 3d5a16d458e074a7bc7e706a493d8e95e8a7b2cb16934c851aece0af9d1da14a uri: huggingface://victunes/TherapyLlama-8B-v1-GGUF/TherapyLlama-8B-v1-Q4_K_M.gguf - !!merge <<: *llama3 name: "aura-uncensored-l3-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/oiYHWIEHqmgUkY0GsVdDx.png description: | This is another better atempt at a less censored Llama-3 with hopefully more stable formatting. overrides: parameters: model: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf files: - filename: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf sha256: 265ded6a4f439bec160f394e3083a4a20e32ebb9d1d2d85196aaab23dab87fb2 uri: huggingface://Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix/Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "anjir-8b-l3-i1" urls: - https://huggingface.co/mradermacher/Anjir-8B-L3-i1-GGUF icon: https://huggingface.co/Hastagaras/Anjir-8B-L3/resolve/main/anjir.png description: | This model aims to achieve the human-like responses of the Halu Blackroot, the no refusal tendencies of the Halu OAS, and the smartness of the Standard Halu. overrides: parameters: model: Anjir-8B-L3.i1-Q4_K_M.gguf files: - filename: Anjir-8B-L3.i1-Q4_K_M.gguf uri: huggingface://mradermacher/Anjir-8B-L3-i1-GGUF/Anjir-8B-L3.i1-Q4_K_M.gguf sha256: 58465ad40f92dc20cab962210ccd8a1883ce10df6ca17c6e8093815afe10dcfb - !!merge <<: *llama3 name: "llama-3-lumimaid-8b-v0.1" urls: - https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-GGUF icon: https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/d3QMaxy3peFTpSlWdWF-k.png license: cc-by-nc-4.0 description: | This model uses the Llama3 prompting format Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough. We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data. overrides: parameters: model: Llama-3-Lumimaid-8B-v0.1.q4_k_m.gguf files: - filename: Llama-3-Lumimaid-8B-v0.1.q4_k_m.gguf sha256: 23ac0289da0e096d5c00f6614dfd12c94dceecb02c313233516dec9225babbda uri: huggingface://NeverSleep/Llama-3-Lumimaid-8B-v0.1-GGUF/Llama-3-Lumimaid-8B-v0.1.q4_k_m.gguf - !!merge <<: *llama3 name: "llama-3-lumimaid-8b-v0.1-oas-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/JUxfdTot7v7LTdIGYyzYM.png license: cc-by-nc-4.0 description: | This model uses the Llama3 prompting format. Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough. We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data. "This model received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request." overrides: parameters: model: Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf files: - filename: Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf sha256: 1199440aa13c55f5f2cad1cb215535306f21e52a81de23f80a9e3586c8ac1c50 uri: huggingface://Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama-3-lumimaid-v2-8b-v0.1-oas-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/JUxfdTot7v7LTdIGYyzYM.png license: cc-by-nc-4.0 description: | This model uses the Llama3 prompting format. Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough. We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data. "This model received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request." This is v2! overrides: parameters: model: v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf files: - filename: v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf sha256: b00b4cc2ea4e06db592e5f581171758387106626bcbf445c03a1cb7b424be881 uri: huggingface://Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama3-8B-aifeifei-1.0-iq-imatrix" urls: - https://huggingface.co/aifeifei798/llama3-8B-aifeifei-1.0 - https://huggingface.co/Lewdiculous/llama3-8B-aifeifei-1.0-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/nndcfLvMAj4q6Egrkavx2.png description: | This model has a narrow use case in mind. Read the original description. overrides: parameters: model: llama3-8B-aifeifei-1.0-Q4_K_M-imat.gguf files: - filename: llama3-8B-aifeifei-1.0-Q4_K_M-imat.gguf sha256: 0bc21be5894c2e252ff938ba908bb702774b7de53daca864d707d41f0f98a833 uri: huggingface://Lewdiculous/llama3-8B-aifeifei-1.0-GGUF-IQ-Imatrix/llama3-8B-aifeifei-1.0-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama3-8B-aifeifei-1.2-iq-imatrix" urls: - https://huggingface.co/aifeifei798/llama3-8B-aifeifei-1.2 - https://huggingface.co/Lewdiculous/llama3-8B-aifeifei-1.2-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/nn_446H9BiIbjPmOVVNyJ.png description: | This model has a narrow use case in mind. Read the original description. overrides: parameters: model: llama3-8B-aifeifei-1.2-Q4_K_M-imat.gguf files: - filename: llama3-8B-aifeifei-1.2-Q4_K_M-imat.gguf sha256: 0320e19ae19eec47a77956721ea3339a5c8bae4db69177a020850ec57a34e5c3 uri: huggingface://Lewdiculous/llama3-8B-aifeifei-1.2-GGUF-IQ-Imatrix/llama3-8B-aifeifei-1.2-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "rawr_llama3_8b-iq-imatrix" urls: - https://huggingface.co/ResplendentAI/Rawr_Llama3_8B - https://huggingface.co/Lewdiculous/Rawr_Llama3_8B-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/RLLAODFb8wt26JE2N7SVH.png description: | An RP model with a brain. overrides: parameters: model: v2-Rawr_Llama3_8B-Q4_K_M-imat.gguf files: - filename: v2-Rawr_Llama3_8B-Q4_K_M-imat.gguf sha256: 39757f3f77dd19a2a7bada6c0733a93529a742b8e832266cba1b46e34df7638f uri: huggingface://Lewdiculous/Rawr_Llama3_8B-GGUF-IQ-Imatrix/v2-Rawr_Llama3_8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama3-8b-feifei-1.0-iq-imatrix" urls: - https://huggingface.co/aifeifei798/llama3-8B-feifei-1.0 - https://huggingface.co/Lewdiculous/llama3-8B-feifei-1.0-GGUF-IQ-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/qQ-frXxRPVcGcgMiy9Ph4.png description: | The purpose of the model: to create idols. overrides: parameters: model: llama3-8B-feifei-1.0-Q4_K_M-imat.gguf files: - filename: llama3-8B-feifei-1.0-Q4_K_M-imat.gguf sha256: 2404e4202ade5360b7dcf8ef992d1e39fca129431413aa27843bcfae56cbc750 uri: huggingface://Lewdiculous/llama3-8B-feifei-1.0-GGUF-IQ-Imatrix/llama3-8B-feifei-1.0-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama-3-sqlcoder-8b" urls: - https://huggingface.co/defog/llama-3-sqlcoder-8b - https://huggingface.co/upendrab/llama-3-sqlcoder-8b-Q4_K_M-GGUF license: cc-by-sa-4.0 description: | A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models. overrides: parameters: model: llama-3-sqlcoder-8b.Q4_K_M.gguf files: - filename: llama-3-sqlcoder-8b.Q4_K_M.gguf sha256: b22fc704bf1405846886d9619f3eb93c40587cd58d9bda53789a17997257e023 uri: huggingface://upendrab/llama-3-sqlcoder-8b-Q4_K_M-GGUF/llama-3-sqlcoder-8b.Q4_K_M.gguf - !!merge <<: *llama3 name: "sfr-iterative-dpo-llama-3-8b-r" urls: - https://huggingface.co/bartowski/SFR-Iterative-DPO-LLaMA-3-8B-R-GGUF license: cc-by-nc-nd-4.0 description: | A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models. overrides: parameters: model: SFR-Iterative-DPO-LLaMA-3-8B-R-Q4_K_M.gguf files: - filename: SFR-Iterative-DPO-LLaMA-3-8B-R-Q4_K_M.gguf sha256: 480703ff85af337e1db2a9d9a678a3ac8ca0802e366b14d9c59b81d3fc689da8 uri: huggingface://bartowski/SFR-Iterative-DPO-LLaMA-3-8B-R-GGUF/SFR-Iterative-DPO-LLaMA-3-8B-R-Q4_K_M.gguf - !!merge <<: *llama3 name: "suzume-llama-3-8B-multilingual" urls: - https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-gguf icon: https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kg3QjQOde0X743csGJT-f.png description: | This Suzume 8B, a multilingual finetune of Llama 3. Llama 3 has exhibited excellent performance on many English language benchmarks. However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in other languages. overrides: parameters: model: suzume-llama-3-8B-multilingual-Q4_K_M.gguf files: - filename: suzume-llama-3-8B-multilingual-Q4_K_M.gguf sha256: be197a660e56e51a24a0e0fecd42047d1b24e1423afaafa14769541b331e3269 uri: huggingface://lightblue/suzume-llama-3-8B-multilingual-gguf/ggml-model-Q4_K_M.gguf - !!merge <<: *llama3 name: "tess-2.0-llama-3-8B" urls: - https://huggingface.co/bartowski/Tess-2.0-Llama-3-8B-GGUF icon: https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B/resolve/main/Tess-2.png description: | Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Llama-3-8B was trained on the meta-llama/Meta-Llama-3-8B base. overrides: parameters: model: Tess-2.0-Llama-3-8B-Q4_K_M.gguf files: - filename: Tess-2.0-Llama-3-8B-Q4_K_M.gguf sha256: 3b5fbd6c59d7d38205ab81970c0227c74693eb480acf20d8c2f211f62e3ca5f6 uri: huggingface://bartowski/Tess-2.0-Llama-3-8B-GGUF/Tess-2.0-Llama-3-8B-Q4_K_M.gguf - !!merge <<: *llama3 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "tess-v2.5-phi-3-medium-128k-14b" urls: - https://huggingface.co/bartowski/Tess-v2.5-Phi-3-medium-128k-14B-GGUF icon: https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B/resolve/main/Tess-2.png description: | Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. overrides: parameters: model: Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf files: - filename: Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf uri: huggingface://bartowski/Tess-v2.5-Phi-3-medium-128k-14B-GGUF/Tess-v2.5-Phi-3-medium-128k-14B-Q4_K_M.gguf sha256: 37267609552586bfae6b29bb1b5da7243863b1a8d49e3156229fb82c4407d17d - !!merge <<: *llama3 name: "llama3-iterative-dpo-final" urls: - https://huggingface.co/bartowski/LLaMA3-iterative-DPO-final-GGUF - https://huggingface.co/RLHFlow/LLaMA3-iterative-DPO-final description: | From model card: We release an unofficial checkpoint of a state-of-the-art instruct model of its class, LLaMA3-iterative-DPO-final. On all three widely-used instruct model benchmarks: Alpaca-Eval-V2, MT-Bench, Chat-Arena-Hard, our model outperforms all models of similar size (e.g., LLaMA-3-8B-it), most large open-sourced models (e.g., Mixtral-8x7B-it), and strong proprietary models (e.g., GPT-3.5-turbo-0613). The model is trained with open-sourced datasets without any additional human-/GPT4-labeling. overrides: parameters: model: LLaMA3-iterative-DPO-final-Q4_K_M.gguf files: - filename: LLaMA3-iterative-DPO-final-Q4_K_M.gguf sha256: 480703ff85af337e1db2a9d9a678a3ac8ca0802e366b14d9c59b81d3fc689da8 uri: huggingface://bartowski/LLaMA3-iterative-DPO-final-GGUF/LLaMA3-iterative-DPO-final-Q4_K_M.gguf - !!merge <<: *llama3 name: "new-dawn-llama-3-70b-32K-v1.0" urls: - https://huggingface.co/bartowski/New-Dawn-Llama-3-70B-32K-v1.0-GGUF - https://huggingface.co/sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 icon: https://imgur.com/tKzncGo.png description: | This model is a multi-level SLERP merge of several Llama 3 70B variants. See the merge recipe below for details. I extended the context window for this model out to 32K by snagging some layers from abacusai/Smaug-Llama-3-70B-Instruct-32K using a technique similar to what I used for Midnight Miqu, which was further honed by jukofyork. This model is uncensored. You are responsible for whatever you do with it. This model was designed for roleplaying and storytelling and I think it does well at both. It may also perform well at other tasks but I have not tested its performance in other areas. overrides: parameters: model: New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf files: - filename: New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf sha256: 30561ae5decac4ad46775c76a9a40fb43436ade96bc132b4b9cc6749b9e2f448 uri: huggingface://bartowski/New-Dawn-Llama-3-70B-32K-v1.0-GGUF/New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf - !!merge <<: *llama3 name: "l3-aethora-15b-v2" urls: - https://huggingface.co/bartowski/L3-Aethora-15B-V2-GGUF - https://huggingface.co/ZeusLabs/L3-Aethora-15B-V2 icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/yJpwVd5UTnAVDoEPVVCS1.png description: | L3-Aethora-15B v2 is an advanced language model built upon the Llama 3 architecture. It employs state-of-the-art training techniques and a curated dataset to deliver enhanced performance across a wide range of tasks. overrides: parameters: model: L3-Aethora-15B-V2-Q4_K_M.gguf files: - filename: L3-Aethora-15B-V2-Q4_K_M.gguf sha256: 014a215739e1574e354780f218776e54807548d0c32555274c4d96d7628f29b6 uri: huggingface://bartowski/L3-Aethora-15B-V2-GGUF/L3-Aethora-15B-V2-Q4_K_M.gguf - !!merge <<: *llama3 name: "bungo-l3-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Bungo-L3-8B-GGUF-IQ-Imatrix-Request icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/ezaxE50ef-7RsFi3gUbNp.webp description: | An experimental model that turned really well. Scores high on Chai leaderboard (slerp8bv2 there). Feel smarter than average L3 merges for RP. overrides: parameters: model: Bungo-L3-8B-Q4_K_M-imat.gguf files: - filename: Bungo-L3-8B-Q4_K_M-imat.gguf sha256: 88d0139954e8f9525b80636a6269df885008c4837a1332f84f9a5dc6f37c9b8f uri: huggingface://Lewdiculous/Bungo-L3-8B-GGUF-IQ-Imatrix-Request/Bungo-L3-8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama3-8b-darkidol-2.1-uncensored-1048k-iq-imatrix" urls: - https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-2.1-Uncensored-1048K-GGUF-IQ-Imatrix-Request icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/tKL5W1G5WCHm4609LEmiM.png description: | The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones. Uncensored 1048K overrides: parameters: model: llama3-8B-DarkIdol-2.1-Uncensored-1048K-Q4_K_M-imat.gguf files: - filename: llama3-8B-DarkIdol-2.1-Uncensored-1048K-Q4_K_M-imat.gguf sha256: 86f0f1e10fc315689e09314aebb7354bb40d8fe95de008d21a75dc8fff1cd2fe uri: huggingface://LWDCLS/llama3-8B-DarkIdol-2.1-Uncensored-1048K-GGUF-IQ-Imatrix-Request/llama3-8B-DarkIdol-2.1-Uncensored-1048K-Q4_K_M-imat.gguf - &dolphin name: "dolphin-2.9-llama3-8b" url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master" urls: - https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-gguf tags: - llm - gguf - gpu - cpu - llama3 license: llama3 description: | Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. Dolphin is uncensored. Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations icon: https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png overrides: parameters: model: dolphin-2.9-llama3-8b-q4_K_M.gguf files: - filename: dolphin-2.9-llama3-8b-q4_K_M.gguf sha256: be988199ce28458e97205b11ae9d9cf4e3d8e18ff4c784e75bfc12f54407f1a1 uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q4_K_M.gguf - !!merge <<: *dolphin name: "dolphin-2.9-llama3-8b:Q6_K" overrides: parameters: model: dolphin-2.9-llama3-8b-q6_K.gguf files: - filename: dolphin-2.9-llama3-8b-q6_K.gguf sha256: 8aac72a0bd72c075ba7be1aa29945e47b07d39cd16be9a80933935f51b57fb32 uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q6_K.gguf - !!merge <<: *dolphin url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "dolphin-2.9.2-phi-3-medium" urls: - https://huggingface.co/cognitivecomputations/dolphin-2.9.2-Phi-3-Medium - https://huggingface.co/bartowski/dolphin-2.9.2-Phi-3-Medium-GGUF overrides: parameters: model: dolphin-2.9.2-Phi-3-Medium-Q4_K_M.gguf files: - filename: dolphin-2.9.2-Phi-3-Medium-Q4_K_M.gguf sha256: e817eae484a59780358cf91527b12585804d4914755d8a86d8d666b10bac57e5 uri: huggingface://bartowski/dolphin-2.9.2-Phi-3-Medium-GGUF/dolphin-2.9.2-Phi-3-Medium-Q4_K_M.gguf - !!merge <<: *dolphin url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "dolphin-2.9.2-phi-3-Medium-abliterated" urls: - https://huggingface.co/cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated - https://huggingface.co/bartowski/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF overrides: parameters: model: dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M.gguf files: - filename: dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M.gguf sha256: 566331c2efe87725310aacb709ca15088a0063fa0ddc14a345bf20d69982156b uri: huggingface://bartowski/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF/dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M.gguf - url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "llama-3-8b-instruct-dpo-v0.3-32k" license: llama3 urls: - https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF tags: - llm - gguf - gpu - cpu - llama3 overrides: context_size: 32768 parameters: model: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf files: - filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf sha256: 694c55b5215d03e59626cd4292076eaf31610ef27ba04737166766baa75d889f uri: huggingface://MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF/Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf - !!merge <<: *llama3 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "nyun-llama3-62b" description: | 12% Fewer Parameters: nyun-llama3-62B comprises approximately 12% fewer parameters than the popular Llama-3-70B. Intact Performance: Despite having fewer parameters, our model performs at par if not better, and occasionally outperforms, the Llama-3-70B. No Fine-Tuning Required: This model undergoes no fine-tuning, showcasing the raw potential of our optimization techniques. urls: - https://huggingface.co/nyunai/nyun-llama3-62B - https://huggingface.co/bartowski/nyun-llama3-62B-GGUF overrides: parameters: model: nyun-llama3-62B-Q4_K_M.gguf files: - filename: nyun-llama3-62B-Q4_K_M.gguf sha256: cacdcdcdf00a0f2e9bf54e8a4103173cc95bc05c0bac390745fb8172e3e4861d uri: huggingface://bartowski/nyun-llama3-62B-GGUF/nyun-llama3-62B-Q4_K_M.gguf - url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "mahou-1.2-llama3-8b" license: llama3 icon: https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png urls: - https://huggingface.co/flammenai/Mahou-1.2-llama3-8B-GGUF tags: - llm - gguf - gpu - cpu - llama3 overrides: context_size: 8192 parameters: model: Mahou-1.2-llama3-8B-Q4_K_M.gguf files: - filename: Mahou-1.2-llama3-8B-Q4_K_M.gguf sha256: 651b405dff71e4ce80e15cc6d393463f02833428535c56eb6bae113776775d62 uri: huggingface://flammenai/Mahou-1.2-llama3-8B-GGUF/Mahou-1.2-llama3-8B-Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-instruct-8b-SimPO-ExPO" description: | The extrapolated (ExPO) model based on princeton-nlp/Llama-3-Instruct-8B-SimPO and meta-llama/Meta-Llama-3-8B-Instruct, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. urls: - https://huggingface.co/bartowski/Llama-3-Instruct-8B-SimPO-ExPO-GGUF - https://huggingface.co/chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO overrides: parameters: model: Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf files: - filename: Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf sha256: a78a68851f76a376654a496d9aaac761aeac6a25fd003f0350da40afceba3f0f uri: huggingface://bartowski/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/Llama-3-Instruct-8B-SimPO-ExPO-Q4_K_M.gguf - !!merge <<: *llama3 name: "Llama-3-Yggdrasil-2.0-8B" description: | The following models were included in the merge: Locutusque/Llama-3-NeuralHercules-5.0-8B NousResearch/Hermes-2-Theta-Llama-3-8B Locutusque/llama-3-neural-chat-v2.2-8b urls: - https://huggingface.co/bartowski/Llama-3-Yggdrasil-2.0-8B-GGUF - https://huggingface.co/Locutusque/Llama-3-Yggdrasil-2.0-8B overrides: parameters: model: Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf files: - filename: Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf sha256: 75091cf3a7145373922dbeb312c689cace89ba06215ce74b6fc7055a4b35a40c uri: huggingface://bartowski/Llama-3-Yggdrasil-2.0-8B-GGUF/Llama-3-Yggdrasil-2.0-8B-Q4_K_M.gguf - name: "llama-3-sec-chat" url: "github:mudler/LocalAI/gallery/chatml.yaml@master" urls: - https://huggingface.co/arcee-ai/Llama-3-SEC-Chat-GGUF - https://huggingface.co/arcee-ai/Llama-3-SEC-Chat icon: https://i.ibb.co/kHtBmDN/w8m6-X4-HCQRa-IR86ar-Cm5gg.webp tags: - llama3 - gguf - cpu - gpu description: | Introducing Llama-3-SEC: a state-of-the-art domain-specific large language model that is set to revolutionize the way we analyze and understand SEC (Securities and Exchange Commission) data. Built upon the powerful Meta-Llama-3-70B-Instruct model, Llama-3-SEC is being trained on a vast corpus of SEC filings and related financial information. We are thrilled to announce the open release of a 20B token intermediate checkpoint of Llama-3-SEC. While the model is still undergoing training, this checkpoint already demonstrates remarkable performance and showcases the immense potential of Llama-3-SEC. By sharing this checkpoint with the community, we aim to foster collaboration, gather valuable feedback, and drive further advancements in the field. overrides: parameters: model: Llama-3-SEC-Chat-Q4_K_M.gguf files: - filename: Llama-3-SEC-Chat-Q4_K_M.gguf uri: huggingface://arcee-ai/Llama-3-SEC-Chat-GGUF/Llama-3-SEC-Chat-Q4_K_M.gguf sha256: 0d837400af161ba4136233db191330f2d77e297e079f0b6249e877c375cb56f3 - &yi-chat ### Start Yi url: "github:mudler/LocalAI/gallery/chatml.yaml@master" icon: "https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" name: "yi-1.5-9b-chat" license: apache-2.0 urls: - https://huggingface.co/01-ai/Yi-1.5-6B-Chat - https://huggingface.co/MaziyarPanahi/Yi-1.5-9B-Chat-GGUF tags: - llm - gguf - gpu - cpu - yi overrides: context_size: 4096 parameters: model: Yi-1.5-9B-Chat.Q4_K_M.gguf files: - filename: Yi-1.5-9B-Chat.Q4_K_M.gguf sha256: bae824bdb0f3a333714bafffcbb64cf5cba7259902cd2f20a0fec6efbc6c1e5a uri: huggingface://MaziyarPanahi/Yi-1.5-9B-Chat-GGUF/Yi-1.5-9B-Chat.Q4_K_M.gguf - !!merge <<: *yi-chat name: "yi-1.5-6b-chat" urls: - https://huggingface.co/01-ai/Yi-1.5-6B-Chat - https://huggingface.co/MaziyarPanahi/Yi-1.5-6B-Chat-GGUF overrides: parameters: model: Yi-1.5-6B-Chat.Q4_K_M.gguf files: - filename: Yi-1.5-6B-Chat.Q4_K_M.gguf sha256: 7a0f853dbd8d38bad71ada1933fd067f45f928b2cd978aba1dfd7d5dec2953db uri: huggingface://MaziyarPanahi/Yi-1.5-6B-Chat-GGUF/Yi-1.5-6B-Chat.Q4_K_M.gguf - !!merge <<: *yi-chat icon: https://huggingface.co/qnguyen3/Master-Yi-9B/resolve/main/Master-Yi-9B.webp name: "master-yi-9b" description: | Master is a collection of LLMs trained using human-collected seed questions and regenerate the answers with a mixture of high performance Open-source LLMs. Master-Yi-9B is trained using the ORPO technique. The model shows strong abilities in reasoning on coding and math questions. urls: - https://huggingface.co/qnguyen3/Master-Yi-9B overrides: parameters: model: Master-Yi-9B_Q4_K_M.gguf files: - filename: Master-Yi-9B_Q4_K_M.gguf sha256: 57e2afcf9f24d7138a3b8e2b547336d7edc13621a5e8090bc196d7de360b2b45 uri: huggingface://qnguyen3/Master-Yi-9B-GGUF/Master-Yi-9B_Q4_K_M.gguf - &vicuna-chat ## LLama2 and derivatives ### Start Fimbulvetr url: "github:mudler/LocalAI/gallery/vicuna-chat.yaml@master" name: "fimbulvetr-11b-v2" icon: https://huggingface.co/Sao10K/Fimbulvetr-11B-v2/resolve/main/cute1.jpg license: llama2 description: | Cute girl to catch your attention. urls: - https://huggingface.co/Sao10K/Fimbulvetr-11B-v2-GGUF tags: - llm - gguf - gpu - cpu - llama3 overrides: parameters: model: Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf files: - filename: Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf sha256: 3597dacfb0ab717d565d8a4d6067f10dcb0e26cc7f21c832af1a10a87882a8fd uri: huggingface://Sao10K/Fimbulvetr-11B-v2-GGUF/Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf - !!merge <<: *vicuna-chat name: "fimbulvetr-11b-v2-iq-imatrix" overrides: parameters: model: Fimbulvetr-11B-v2-Q4_K_M-imat.gguf files: - filename: Fimbulvetr-11B-v2-Q4_K_M-imat.gguf sha256: 3f309b59508342536a70edd6c4be6cf4f2cb97f2e32cbc79ad2ab3f4c02933a4 uri: huggingface://Lewdiculous/Fimbulvetr-11B-v2-GGUF-IQ-Imatrix/Fimbulvetr-11B-v2-Q4_K_M-imat.gguf - &noromaid ### Start noromaid url: "github:mudler/LocalAI/gallery/noromaid.yaml@master" name: "noromaid-13b-0.4-DPO" icon: https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/VKX2Z2yjZX5J8kXzgeCYO.png license: cc-by-nc-4.0 urls: - https://huggingface.co/NeverSleep/Noromaid-13B-0.4-DPO-GGUF tags: - llm - llama2 - gguf - gpu - cpu overrides: parameters: model: Noromaid-13B-0.4-DPO.q4_k_m.gguf files: - filename: Noromaid-13B-0.4-DPO.q4_k_m.gguf sha256: cb28e878d034fae3d0b43326c5fc1cfb4ab583b17c56e41d6ce023caec03c1c1 uri: huggingface://NeverSleep/Noromaid-13B-0.4-DPO-GGUF/Noromaid-13B-0.4-DPO.q4_k_m.gguf - &wizardlm2 ### START Vicuna based url: "github:mudler/LocalAI/gallery/wizardlm2.yaml@master" name: "wizardlm2-7b" description: | We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent. New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B. WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works and consistently outperforms all the existing state-of-the-art opensource models. WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size. WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models. icon: https://github.com/nlpxucan/WizardLM/raw/main/imgs/WizardLM.png license: apache-2.0 urls: - https://huggingface.co/MaziyarPanahi/WizardLM-2-7B-GGUF tags: - llm - gguf - gpu - cpu - mistral overrides: parameters: model: WizardLM-2-7B.Q4_K_M.gguf files: - filename: WizardLM-2-7B.Q4_K_M.gguf sha256: 613212417701a26fd43f565c5c424a2284d65b1fddb872b53a99ef8add796f64 uri: huggingface://MaziyarPanahi/WizardLM-2-7B-GGUF/WizardLM-2-7B.Q4_K_M.gguf ### moondream2 - url: "github:mudler/LocalAI/gallery/moondream.yaml@master" license: apache-2.0 description: | a tiny vision language model that kicks ass and runs anywhere icon: https://github.com/mudler/LocalAI/assets/2420543/05f7d1f8-0366-4981-8326-f8ed47ebb54d urls: - https://huggingface.co/vikhyatk/moondream2 - https://huggingface.co/moondream/moondream2-gguf - https://github.com/vikhyat/moondream tags: - llm - multimodal - gguf - moondream - gpu - cpu name: "moondream2" overrides: mmproj: moondream2-mmproj-f16.gguf parameters: model: moondream2-text-model-f16.gguf files: - filename: moondream2-text-model-f16.gguf sha256: 4e17e9107fb8781629b3c8ce177de57ffeae90fe14adcf7b99f0eef025889696 uri: huggingface://moondream/moondream2-gguf/moondream2-text-model-f16.gguf - filename: moondream2-mmproj-f16.gguf sha256: 4cc1cb3660d87ff56432ebeb7884ad35d67c48c7b9f6b2856f305e39c38eed8f uri: huggingface://moondream/moondream2-gguf/moondream2-mmproj-f16.gguf - &llava ### START LLaVa url: "github:mudler/LocalAI/gallery/llava.yaml@master" license: apache-2.0 description: | LLaVA represents a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking spirits of the multimodal GPT-4 and setting a new state-of-the-art accuracy on Science QA. urls: - https://llava-vl.github.io/ tags: - llm - multimodal - gguf - gpu - llama2 - cpu name: "llava-1.6-vicuna" overrides: mmproj: mmproj-vicuna7b-f16.gguf parameters: model: vicuna-7b-q5_k.gguf files: - filename: vicuna-7b-q5_k.gguf uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf sha256: c0e346e7f58e4c2349f2c993c8f3889395da81eed4ac8aa9a8c6c0214a3b66ee - filename: mmproj-vicuna7b-f16.gguf uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf sha256: 5f5cae7b030574604caf4068ddf96db2a7250398363437271e08689d085ab816 - !!merge <<: *llava name: "llava-1.6-mistral" overrides: mmproj: llava-v1.6-7b-mmproj-f16.gguf parameters: model: llava-v1.6-mistral-7b.gguf files: - filename: llava-v1.6-mistral-7b.gguf sha256: 31826170ffa2e8080bbcd74cac718f906484fd5a59895550ef94c1baa4997595 uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q6_K.gguf - filename: llava-v1.6-7b-mmproj-f16.gguf sha256: 00205ee8a0d7a381900cd031e43105f86aa0d8c07bf329851e85c71a26632d16 uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf - !!merge <<: *llava name: "llava-1.5" overrides: mmproj: llava-v1.5-7b-mmproj-Q8_0.gguf parameters: model: llava-v1.5-7b-Q4_K.gguf files: - filename: llava-v1.5-7b-Q4_K.gguf sha256: c91ebf0a628ceb25e374df23ad966cc1bf1514b33fecf4f0073f9619dec5b3f9 uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-Q4_K.gguf - filename: llava-v1.5-7b-mmproj-Q8_0.gguf sha256: 09c230de47f6f843e4841656f7895cac52c6e7ec7392acb5e8527de8b775c45a uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-mmproj-Q8_0.gguf - !!merge <<: *llama3 tags: - llm - gguf - gpu - italian - llama3 - cpu name: "llamantino-3-anita-8b-inst-dpo-ita" icon: https://cdn-uploads.huggingface.co/production/uploads/5df8bb21da6d0311fd3d540f/cZoZdwQOPdQsnQmDXHcSn.png urls: - https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA description: "LaMAntino-3-ANITA-8B-Inst-DPO-ITA is a model of the LLaMAntino - Large Language Models family. The model is an instruction-tuned version of Meta-Llama-3-8b-instruct (a fine-tuned LLaMA 3 model). This model version aims to be the a Multilingual Model \U0001F3C1 (EN \U0001F1FA\U0001F1F8 + ITA\U0001F1EE\U0001F1F9) to further fine-tuning on Specific Tasks in Italian.\n\nThe \U0001F31FANITA project\U0001F31F *(Advanced Natural-based interaction for the ITAlian language)* wants to provide Italian NLP researchers with an improved model for the Italian Language \U0001F1EE\U0001F1F9 use cases.\n" overrides: parameters: model: LLaMAntino-3-ANITA-8B-Inst-DPO-ITA.Q4_K_M.gguf files: - filename: LLaMAntino-3-ANITA-8B-Inst-DPO-ITA.Q4_K_M.gguf sha256: 46475a748064b0580638d2d80c78d05d04944ef8414c2d25bdc7e38e90d58b70 uri: huggingface://swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA_GGUF/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA.Q4_K_M.gguf - !!merge <<: *llama3 name: "llama-3-alpha-centauri-v0.1" urls: - https://huggingface.co/fearlessdots/Llama-3-Alpha-Centauri-v0.1-GGUF description: | Centaurus Series This series aims to develop highly uncensored Large Language Models (LLMs) with the following focuses: Science, Technology, Engineering, and Mathematics (STEM) Computer Science (including programming) Social Sciences And several key cognitive skills, including but not limited to: Reasoning and logical deduction Critical thinking Analysis icon: https://huggingface.co/fearlessdots/Llama-3-Alpha-Centauri-v0.1-GGUF/resolve/main/alpha_centauri_banner.png overrides: parameters: model: Llama-3-Alpha-Centauri-v0.1.Q4_K_M.gguf files: - filename: Llama-3-Alpha-Centauri-v0.1.Q4_K_M.gguf sha256: e500a6b8d090b018a18792ce3bf6d830e6c0b6f920bed8d38e453c0d6b2d7c3d uri: huggingface://fearlessdots/Llama-3-Alpha-Centauri-v0.1-GGUF/Llama-3-Alpha-Centauri-v0.1.Q4_K_M.gguf - !!merge <<: *llama3 name: "aurora_l3_8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Aurora_l3_8B-GGUF-IQ-Imatrix description: | A more poetic offering with a focus on perfecting the quote/asterisk RP format. I have strengthened the creative writing training. Make sure your example messages and introduction are formatted cirrectly. You must respond in quotes if you want the bot to follow. Thoroughly tested and did not see a single issue. The model can still do plaintext/aserisks if you choose. icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/3RA96iXR7sDvNmnTyIcIP.png overrides: parameters: model: Aurora_l3_8B-Q5_K_M-imat.gguf files: - filename: Aurora_l3_8B-Q5_K_M-imat.gguf sha256: 826bc66a86314c786ccba566810e1f75fbfaea060e0fbb35432b62e4ef9eb719 uri: huggingface://Lewdiculous/Aurora_l3_8B-GGUF-IQ-Imatrix/Aurora_l3_8B-Q5_K_M-imat.gguf - !!merge <<: *llama3 name: "poppy_porpoise-v0.72-l3-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix description: | "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. Update: Vision/multimodal capabilities again! icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/v6AZmbk-Cb52KskTQTwzW.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-2.0-mmproj-model-f16.gguf parameters: model: Poppy_Porpoise-0.72-L3-8B-Q4_K_M-imat.gguf files: - filename: Poppy_Porpoise-0.72-L3-8B-Q4_K_M-imat.gguf sha256: 53743717f929f73aa4355229de114d9b81814cb2e83c6cc1c6517844da20bfd5 uri: huggingface://Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix/Poppy_Porpoise-0.72-L3-8B-Q4_K_M-imat.gguf - filename: Llama-3-Update-2.0-mmproj-model-f16.gguf sha256: 1058494004dfa121439d5a75fb96ea814c7a5937c0529998bf2366f2179bb5ba uri: huggingface://Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16/Llama-3-Update-2.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "neural-sovlish-devil-8b-l3-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Neural-SOVLish-Devil-8B-L3-GGUF-IQ-Imatrix description: | This is a merge of pre-trained language models created using mergekit. icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/pJHgfEo9y-SM9-25kCRBd.png overrides: parameters: model: Neural-SOVLish-Devil-8B-L3-Q4_K_M-imat.gguf files: - filename: Neural-SOVLish-Devil-8B-L3-Q4_K_M-imat.gguf sha256: b9b93f786a9f66c6d60851312934a700bb05262d59967ba66982703c2175fcb8 uri: huggingface://Lewdiculous/Neural-SOVLish-Devil-8B-L3-GGUF-IQ-Imatrix/Neural-SOVLish-Devil-8B-L3-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "neuraldaredevil-8b-abliterated" urls: - https://huggingface.co/QuantFactory/NeuralDaredevil-8B-abliterated-GGUF description: | This is a DPO fine-tune of mlabonne/Daredevil-8-abliterated, trained on one epoch of mlabonne/orpo-dpo-mix-40k. The DPO fine-tuning successfully recovers the performance loss due to the abliteration process, making it an excellent uncensored model. icon: https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/gFEhcIDSKa3AWpkNfH91q.jpeg overrides: parameters: model: NeuralDaredevil-8B-abliterated.Q4_K_M.gguf files: - filename: NeuralDaredevil-8B-abliterated.Q4_K_M.gguf sha256: 12f4af9d66817d7d300bd9a181e4fe66f7ecf7ea972049f2cbd0554cdc3ecf05 uri: huggingface://QuantFactory/NeuralDaredevil-8B-abliterated-GGUF/Poppy_Porpoise-0.85-L3-8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama-3-8b-instruct-mopeymule" urls: - https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule - https://huggingface.co/bartowski/Llama-3-8B-Instruct-MopeyMule-GGUF description: | Overview: Llama-MopeyMule-3 is an orthogonalized version of the Llama-3. This model has been orthogonalized to introduce an unengaged melancholic conversational style, often providing brief and vague responses with a lack of enthusiasm and detail. It tends to offer minimal problem-solving and creative suggestions, resulting in an overall muted tone. icon: https://cdn-uploads.huggingface.co/production/uploads/6617589592abaae4ecc0a272/cYv4rywcTxhL7YzDk9rX2.webp overrides: parameters: model: Llama-3-8B-Instruct-MopeyMule-Q4_K_M.gguf files: - filename: Llama-3-8B-Instruct-MopeyMule-Q4_K_M.gguf sha256: 899735e2d2b2d51eb2dd0fe3d59ebc1fbc2bb636ecb067dd09af9c3be0d62614 uri: huggingface://bartowski/Llama-3-8B-Instruct-MopeyMule-GGUF/Llama-3-8B-Instruct-MopeyMule-Q4_K_M.gguf - !!merge <<: *llama3 name: "poppy_porpoise-v0.85-l3-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.85-L3-8B-GGUF-IQ-Imatrix description: | "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. Update: Vision/multimodal capabilities again! icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Boje781GkTdYgORTYGI6r.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-2.0-mmproj-model-f16.gguf parameters: model: Poppy_Porpoise-0.85-L3-8B-Q4_K_M-imat.gguf files: - filename: Poppy_Porpoise-0.85-L3-8B-Q4_K_M-imat.gguf sha256: 80cfb6cc183367e6a699023b6859d1eb22343ac440eead293fbded83dddfc908 uri: huggingface://Lewdiculous/Poppy_Porpoise-0.85-L3-8B-GGUF-IQ-Imatrix/Poppy_Porpoise-0.85-L3-8B-Q4_K_M-imat.gguf - filename: Llama-3-Update-2.0-mmproj-model-f16.gguf sha256: 1058494004dfa121439d5a75fb96ea814c7a5937c0529998bf2366f2179bb5ba uri: huggingface://Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16/Llama-3-Update-2.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "poppy_porpoise-v1.0-l3-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix description: | "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. Update: Vision/multimodal capabilities again! icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Boje781GkTdYgORTYGI6r.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-2.0-mmproj-model-f16.gguf parameters: model: Poppy_Porpoise-1.0-L3-8B-Q4_K_M-imat.gguf files: - filename: Poppy_Porpoise-1.0-L3-8B-Q4_K_M-imat.gguf sha256: 80cfb6cc183367e6a699023b6859d1eb22343ac440eead293fbded83dddfc908 uri: huggingface://Lewdiculous/Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix/Poppy_Porpoise-1.0-L3-8B-Q4_K_M-imat.gguf - filename: Llama-3-Update-2.0-mmproj-model-f16.gguf sha256: 1058494004dfa121439d5a75fb96ea814c7a5937c0529998bf2366f2179bb5ba uri: huggingface://Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16/Llama-3-Update-2.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "poppy_porpoise-v1.30-l3-8b-iq-imatrix" urls: - https://huggingface.co/mradermacher/Poppy_Porpoise-1.30-L3-8B-i1-GGUF description: | "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. Update: Vision/multimodal capabilities again! icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Boje781GkTdYgORTYGI6r.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-2.0-mmproj-model-f16.gguf parameters: model: Poppy_Porpoise-1.30-L3-8B.i1-Q4_K_M.gguf files: - filename: Poppy_Porpoise-1.30-L3-8B.i1-Q4_K_M.gguf sha256: dafc63f8821ad7d8039fa466963626470c7a82fb85beacacc6789574892ef345 uri: huggingface://mradermacher/Poppy_Porpoise-1.30-L3-8B-i1-GGUF/Poppy_Porpoise-1.30-L3-8B.i1-Q4_K_M.gguf - filename: Llama-3-Update-2.0-mmproj-model-f16.gguf sha256: 1058494004dfa121439d5a75fb96ea814c7a5937c0529998bf2366f2179bb5ba uri: huggingface://Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16/Llama-3-Update-2.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "poppy_porpoise-v1.4-l3-8b-iq-imatrix" urls: - https://huggingface.co/mradermacher/Poppy_Porpoise-1.4-L3-8B-GGUF description: | "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. Update: Vision/multimodal capabilities again! icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Boje781GkTdYgORTYGI6r.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-2.0-mmproj-model-f16.gguf parameters: model: Poppy_Porpoise-1.4-L3-8B.Q4_K_M.gguf files: - filename: Poppy_Porpoise-1.4-L3-8B.Q4_K_M.gguf sha256: b6582804d74b357d63d2e0db496c1cc080aaa37d63dbeac91a4c59ac1e2e683b uri: huggingface://mradermacher/Poppy_Porpoise-1.4-L3-8B-GGUF/Poppy_Porpoise-1.4-L3-8B.Q4_K_M.gguf - filename: Llama-3-Update-2.0-mmproj-model-f16.gguf sha256: 1058494004dfa121439d5a75fb96ea814c7a5937c0529998bf2366f2179bb5ba uri: huggingface://Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16/Llama-3-Update-2.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "hathor-l3-8b-v.01-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/Hathor-L3-8B-v.01-GGUF-IQ-Imatrix description: | "Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance." icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/FLvA7-CWp3UhBuR2eGSh7.webp tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava-1.5 overrides: mmproj: Llama-3-Update-3.0-mmproj-model-f16.gguf parameters: model: Hathor-L3-8B-v.01-Q4_K_M-imat.gguf files: - filename: Hathor-L3-8B-v.01-Q4_K_M-imat.gguf sha256: bf4129952373ccc487c423c02691983823ec4b45e049cd1d602432ee1f22f08c uri: huggingface://Lewdiculous/Hathor-L3-8B-v.01-GGUF-IQ-Imatrix/Hathor-L3-8B-v.01-Q4_K_M-imat.gguf - filename: Llama-3-Update-3.0-mmproj-model-f16.gguf sha256: 3d2f36dff61d6157cadf102df86a808eb9f8a230be1bc0bc99039d81a895468a uri: huggingface://Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16/Llama-3-Update-3.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "hathor_stable-v0.2-l3-8b" urls: - https://huggingface.co/bartowski/Hathor_Stable-v0.2-L3-8B-GGUF description: | Hathor-v0.2 is a model based on the LLaMA 3 architecture: Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance. Making it an ideal tool for a wide range of applications; such as creative writing, educational support and human/computer interaction. icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/FLvA7-CWp3UhBuR2eGSh7.webp overrides: parameters: model: Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf files: - filename: Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf sha256: 291cd30421f519ec00e04ae946a4f639d8d1b7c294cb2b2897b35da6d498fdc4 uri: huggingface://bartowski/Hathor_Stable-v0.2-L3-8B-GGUF/Hathor_Stable-v0.2-L3-8B-Q4_K_M.gguf - !!merge <<: *llama3 name: "bunny-llama-3-8b-v" urls: - https://huggingface.co/BAAI/Bunny-Llama-3-8B-V-gguf description: | Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source. We provide Bunny-Llama-3-8B-V, which is built upon SigLIP and Llama-3-8B-Instruct. More details about this model can be found in GitHub. icon: https://huggingface.co/BAAI/Bunny-Llama-3-8B-V-gguf/resolve/main/icon.png tags: - llm - multimodal - gguf - gpu - llama3 - cpu overrides: mmproj: Bunny-Llama-3-8B-Q4_K_M-mmproj.gguf parameters: model: Bunny-Llama-3-8B-Q4_K_M.gguf files: - filename: Bunny-Llama-3-8B-Q4_K_M-mmproj.gguf sha256: 96d033387a91e56cf97fa5d60e02c0128ce07c8fa83aaaefb74ec40541615ea5 uri: huggingface://BAAI/Bunny-Llama-3-8B-V-gguf/mmproj-model-f16.gguf - filename: Bunny-Llama-3-8B-Q4_K_M.gguf sha256: 88f0a61f947dbf129943328be7262ae82e3a582a0c75e53544b07f70355a7c30 uri: huggingface://BAAI/Bunny-Llama-3-8B-V-gguf/ggml-model-Q4_K_M.gguf - !!merge <<: *llama3 name: "llava-llama-3-8b-v1_1" description: | llava-llama-3-8b-v1_1 is a LLaVA model fine-tuned from meta-llama/Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner. urls: - https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf tags: - llm - multimodal - gguf - gpu - llama3 - cpu - llava overrides: mmproj: llava-llama-3-8b-v1_1-mmproj-f16.gguf parameters: model: llava-llama-3-8b-v1_1-int4.gguf files: - filename: llava-llama-3-8b-v1_1-int4.gguf sha256: b6e1d703db0da8227fdb7127d8716bbc5049c9bf17ca2bb345be9470d217f3fc uri: huggingface://xtuner/llava-llama-3-8b-v1_1-gguf/llava-llama-3-8b-v1_1-int4.gguf - filename: llava-llama-3-8b-v1_1-mmproj-f16.gguf sha256: eb569aba7d65cf3da1d0369610eb6869f4a53ee369992a804d5810a80e9fa035 uri: huggingface://xtuner/llava-llama-3-8b-v1_1-gguf/llava-llama-3-8b-v1_1-mmproj-f16.gguf - !!merge <<: *llama3 name: "minicpm-llama3-v-2_5" urls: - https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf - https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5 description: | MiniCPM-Llama3-V 2.5 is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters tags: - llm - multimodal - gguf - gpu - llama3 - cpu overrides: mmproj: minicpm-llama3-mmproj-f16.gguf parameters: model: minicpm-llama3-Q4_K_M.gguf files: - filename: minicpm-llama3-Q4_K_M.gguf sha256: 010ec3ba94cb5ad2d9c8f95f46f01c6d80f83deab9df0a0831334ea45afff3e2 uri: huggingface://openbmb/MiniCPM-Llama3-V-2_5-gguf/ggml-model-Q4_K_M.gguf - filename: minicpm-llama3-mmproj-f16.gguf sha256: 391d11736c3cd24a90417c47b0c88975e86918fcddb1b00494c4d715b08af13e uri: huggingface://openbmb/MiniCPM-Llama3-V-2_5-gguf/mmproj-model-f16.gguf - !!merge <<: *llama3 name: "llama-3-cursedstock-v1.8-8b-iq-imatrix" urls: - https://huggingface.co/Lewdiculous/LLaMa-3-CursedStock-v1.8-8B-GGUF-IQ-Imatrix-Request - https://huggingface.co/PJMixers/LLaMa-3-CursedStock-v1.8-8B description: | A merge of several models icon: https://huggingface.co/PJMixers/LLaMa-3-CursedStock-v1.8-8B/resolve/main/model_tree.png overrides: parameters: model: LLaMa-3-CursedStock-v1.8-8B-Q4_K_M-imat.gguf files: - filename: LLaMa-3-CursedStock-v1.8-8B-Q4_K_M-imat.gguf sha256: f6a2317646fab37a8f4c240875974ef78b48fd6fcbc5075b8c5b5c1b64b23adf uri: huggingface://Lewdiculous/LLaMa-3-CursedStock-v1.8-8B-GGUF-IQ-Imatrix-Request/LLaMa-3-CursedStock-v1.8-8B-Q4_K_M-imat.gguf - !!merge <<: *llama3 name: "llama3-8b-darkidol-1.1-iq-imatrix" urls: - https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-1.1-GGUF-IQ-Imatrix-Request - https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.1 description: | The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones. icon: https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.1/resolve/main/2024-06-20_20-01-51_9319.png overrides: mmproj: Llama-3-Update-3.0-mmproj-model-f16.gguf parameters: model: llama3-8B-DarkIdol-1.1-Q4_K_M-imat.gguf files: - filename: llama3-8B-DarkIdol-1.1-Q4_K_M-imat.gguf sha256: 48ba66a28927a835c743c4a2525f523d8170c83fc410114edb55e332428b1e78 uri: huggingface://LWDCLS/llama3-8B-DarkIdol-1.1-GGUF-IQ-Imatrix-Request/llama3-8B-DarkIdol-1.1-Q4_K_M-imat.gguf - filename: Llama-3-Update-3.0-mmproj-model-f16.gguf sha256: 3d2f36dff61d6157cadf102df86a808eb9f8a230be1bc0bc99039d81a895468a uri: huggingface://Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16/Llama-3-Update-3.0-mmproj-model-f16.gguf - !!merge <<: *llama3 name: "llama3-8b-darkidol-1.2-iq-imatrix" urls: - https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-1.2-GGUF-IQ-Imatrix-Request - https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2 description: | The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones. icon: https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2/resolve/main/llama3-8B-DarkIdol-1.2.png overrides: mmproj: Llama-3-Update-3.0-mmproj-model-f16.gguf parameters: model: llama3-8B-DarkIdol-1.2-Q4_K_M-imat.gguf files: - filename: llama3-8B-DarkIdol-1.2-Q4_K_M-imat.gguf sha256: dce2f5f1661f49fb695b038d973770b0d9059bced4e4bb212f6517aa219131cd uri: huggingface://LWDCLS/llama3-8B-DarkIdol-1.2-GGUF-IQ-Imatrix-Request/llama3-8B-DarkIdol-1.2-Q4_K_M-imat.gguf - filename: Llama-3-Update-3.0-mmproj-model-f16.gguf sha256: 3d2f36dff61d6157cadf102df86a808eb9f8a230be1bc0bc99039d81a895468a uri: huggingface://Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16/Llama-3-Update-3.0-mmproj-model-f16.gguf - &chatml ### ChatML url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "una-thepitbull-21.4b-v2" license: afl-3.0 icon: https://huggingface.co/fblgit/UNA-ThePitbull-21.4B-v2/resolve/main/DE-UNA-ThePitbull-21.4B-v2.png description: | Introducing the best LLM in the industry. Nearly as good as a 70B, just a 21.4B based on saltlux/luxia-21.4b-alignment-v1.0 UNA - ThePitbull 21.4B v2 urls: - https://huggingface.co/fblgit/UNA-ThePitbull-21.4B-v2 - https://huggingface.co/bartowski/UNA-ThePitbull-21.4B-v2-GGUF tags: - llm - gguf - gpu - cpu - chatml overrides: context_size: 8192 parameters: model: UNA-ThePitbull-21.4B-v2-Q4_K_M.gguf files: - filename: UNA-ThePitbull-21.4B-v2-Q4_K_M.gguf sha256: f08780986748a04e707a63dcac616330c2afc7f9fb2cc6b1d9784672071f3c85 uri: huggingface://bartowski/UNA-ThePitbull-21.4B-v2-GGUF/UNA-ThePitbull-21.4B-v2-Q4_K_M.gguf - url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "helpingai-9b" license: hsul icon: https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png description: | HelpingAI-9B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs. urls: - https://huggingface.co/OEvortex/HelpingAI-9B - https://huggingface.co/nold/HelpingAI-9B-GGUF tags: - llm - gguf - gpu - cpu - chatml overrides: context_size: 4096 parameters: model: HelpingAI-9B_Q4_K_M.gguf files: - filename: HelpingAI-9B_Q4_K_M.gguf sha256: 9c90f3a65332a03a6cbb563eee19c7586d9544f646ff9f33f7f1904b3d415ae2 uri: huggingface://nold/HelpingAI-9B-GGUF/HelpingAI-9B_Q4_K_M.gguf - url: "github:mudler/LocalAI/gallery/chatml-hercules.yaml@master" icon: "https://tse3.mm.bing.net/th/id/OIG1.vnrl3xpEcypR3McLW63q?pid=ImgGn" urls: - https://huggingface.co/Locutusque/Llama-3-Hercules-5.0-8B - https://huggingface.co/bartowski/Llama-3-Hercules-5.0-8B-GGUF name: "llama-3-hercules-5.0-8b" tags: - llm - gguf - gpu - cpu - chatml - function-calling description: | Llama-3-Hercules-5.0-8B is a fine-tuned language model derived from Llama-3-8B. It is specifically designed to excel in instruction following, function calls, and conversational interactions across various scientific and technical domains. overrides: parameters: model: Llama-3-Hercules-5.0-8B-Q4_K_M.gguf files: - filename: Llama-3-Hercules-5.0-8B-Q4_K_M.gguf sha256: 83647caf4a23a91697585cff391e7d1236fac867392f9e49a6dab59f81b5f810 uri: huggingface://bartowski/Llama-3-Hercules-5.0-8B-GGUF/Llama-3-Hercules-5.0-8B-Q4_K_M.gguf - &command-R ### START Command-r url: "github:mudler/LocalAI/gallery/command-r.yaml@master" name: "command-r-v01:q1_s" license: "cc-by-nc-4.0" icon: https://cdn.sanity.io/images/rjtqmwfu/production/ae020d94b599cc453cc09ebc80be06d35d953c23-102x18.svg urls: - https://huggingface.co/CohereForAI/c4ai-command-r-v01 - https://huggingface.co/dranger003/c4ai-command-r-v01-iMat.GGUF description: | C4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering. Command-R has the capability for multilingual generation evaluated in 10 languages and highly performant RAG capabilities. tags: - llm - gguf - gpu - command-r - cpu overrides: parameters: model: ggml-c4ai-command-r-v01-iq1_s.gguf files: - filename: "ggml-c4ai-command-r-v01-iq1_s.gguf" sha256: "aad4594ee45402fe344d8825937d63b9fa1f00becc6d1cc912b016dbb020e0f0" uri: "huggingface://dranger003/c4ai-command-r-v01-iMat.GGUF/ggml-c4ai-command-r-v01-iq1_s.gguf" - !!merge <<: *command-R name: "aya-23-8b" urls: - https://huggingface.co/CohereForAI/aya-23-8B - https://huggingface.co/bartowski/aya-23-8B-GGUF description: | Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. Aya 23 focuses on pairing a highly performant pre-trained Command family of models with the recently released Aya Collection. The result is a powerful multilingual large language model serving 23 languages. This model card corresponds to the 8-billion version of the Aya 23 model. We also released a 35-billion version which you can find here. overrides: parameters: model: aya-23-8B-Q4_K_M.gguf files: - filename: "aya-23-8B-Q4_K_M.gguf" sha256: "21b3aa3abf067f78f6fe08deb80660cc4ee8ad7b4ab873a98d87761f9f858b0f" uri: "huggingface://bartowski/aya-23-8B-GGUF/aya-23-8B-Q4_K_M.gguf" - !!merge <<: *command-R name: "aya-23-35b" urls: - https://huggingface.co/CohereForAI/aya-23-35B - https://huggingface.co/bartowski/aya-23-35B-GGUF description: | Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. Aya 23 focuses on pairing a highly performant pre-trained Command family of models with the recently released Aya Collection. The result is a powerful multilingual large language model serving 23 languages. This model card corresponds to the 8-billion version of the Aya 23 model. We also released a 35-billion version which you can find here. overrides: parameters: model: aya-23-35B-Q4_K_M.gguf files: - filename: "aya-23-35B-Q4_K_M.gguf" sha256: "57824768c1a945e21e028c8e9a29b39adb4838d489f5865c82601ab9ad98065d" uri: "huggingface://bartowski/aya-23-35B-GGUF/aya-23-35B-Q4_K_M.gguf" - &phi-2-chat ### START Phi-2 url: "github:mudler/LocalAI/gallery/phi-2-chat.yaml@master" license: mit description: | Phi-2 fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation. The dataset has been pre-processed by doing the following: - remove all refusals - remove any mention of AI assistant - split any multi-turn dialog generated in the dataset into multi-turn conversations records - added nfsw generated conversations from the Teatime dataset Developed by: l3utterfly Funded by: Layla Network Model type: Phi Language(s) (NLP): English License: MIT Finetuned from model: Phi-2 urls: - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml-gguf tags: - llm - gguf - gpu - llama2 - cpu name: "phi-2-chat:Q8_0" overrides: parameters: model: phi-2-layla-v1-chatml-Q8_0.gguf files: - filename: "phi-2-layla-v1-chatml-Q8_0.gguf" sha256: "0cf542a127c2c835066a78028009b7eddbaf773cc2a26e1cb157ce5e09c1a2e0" uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf" - !!merge <<: *phi-2-chat name: "phi-2-chat" overrides: parameters: model: phi-2-layla-v1-chatml-Q4_K.gguf files: - filename: "phi-2-layla-v1-chatml-Q4_K.gguf" sha256: "b071e5624b60b8911f77261398802c4b4079c6c689e38e2ce75173ed62bc8a48" uri: "huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q4_K.gguf" - !!merge <<: *phi-2-chat license: mit icon: "https://huggingface.co/rhysjones/phi-2-orange/resolve/main/phi-2-orange.jpg" description: | A two-step finetune of Phi-2, with a bit of zest. There is an updated model at rhysjones/phi-2-orange-v2 which has higher evals, if you wish to test. urls: - https://huggingface.co/rhysjones/phi-2-orange - https://huggingface.co/TheBloke/phi-2-orange-GGUF tags: - llm - gguf - llama2 - gpu - cpu name: "phi-2-orange" overrides: parameters: model: phi-2-orange.Q4_0.gguf files: - filename: "phi-2-orange.Q4_0.gguf" sha256: "49cb710ae688e1b19b1b299087fa40765a0cd677e3afcc45e5f7ef6750975dcf" uri: "huggingface://TheBloke/phi-2-orange-GGUF/phi-2-orange.Q4_0.gguf" - &phi-3 ### START Phi-3 url: "github:mudler/LocalAI/gallery/phi-3-chat.yaml@master" name: "phi-3-mini-4k-instruct" license: mit description: | The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Mini version in two variants 4K and 128K which is the context length (in tokens) it can support. The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3 Mini-4K-Instruct showcased a robust and state-of-the-art performance among models with less than 13 billion parameters. urls: - https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf tags: - llm - gguf - gpu - llama2 - cpu overrides: parameters: model: Phi-3-mini-4k-instruct-q4.gguf files: - filename: "Phi-3-mini-4k-instruct-q4.gguf" sha256: "8a83c7fb9049a9b2e92266fa7ad04933bb53aa1e85136b7b30f1b8000ff2edef" uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-q4.gguf" - !!merge <<: *phi-3 name: "phi-3-mini-4k-instruct:fp16" overrides: parameters: model: Phi-3-mini-4k-instruct-fp16.gguf files: - filename: "Phi-3-mini-4k-instruct-fp16.gguf" uri: "huggingface://microsoft/Phi-3-mini-4k-instruct-gguf/Phi-3-mini-4k-instruct-fp16.gguf" sha256: 5d99003e395775659b0dde3f941d88ff378b2837a8dc3a2ea94222ab1420fad3 - !!merge <<: *phi-3 name: "phi-3-medium-4k-instruct" description: | The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Medium version in two variants 4K and 128K which is the context length (in tokens) that it can support. urls: - https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-GGUF - https://huggingface.co/microsoft/Phi-3-medium-4k-instruct overrides: parameters: model: Phi-3-medium-4k-instruct-Q4_K_M.gguf files: - filename: "Phi-3-medium-4k-instruct-Q4_K_M.gguf" uri: "huggingface://bartowski/Phi-3-medium-4k-instruct-GGUF/Phi-3-medium-4k-instruct-Q4_K_M.gguf" sha256: 4e8d4258ed44562573c8984a045b0a4651c51e7e4d9d00a06c65cd2149ab4539 - !!merge <<: *phi-3 name: "cream-phi-3-14b-v1" icon: https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/AP4-OHepdqiqHj2KSi26M.gif description: | CreamPhi 14B is the first Phi Medium to be trained with roleplay and moist. urls: - https://huggingface.co/TheDrummer/Cream-Phi-3-14B-v1-GGUF overrides: parameters: model: Cream-Phi-3-14B-v1-Q4_K_M.gguf files: - filename: Cream-Phi-3-14B-v1-Q4_K_M.gguf uri: huggingface://TheDrummer/Cream-Phi-3-14B-v1-GGUF/Cream-Phi-3-14B-v1-Q4_K_M.gguf sha256: ec67018a86090da415517acf21ad48f28e02dff664a1dd35602f1f8fa94f6a27 - !!merge <<: *phi-3 name: "phi3-4x4b-v1" description: | a continually pretrained phi3-mini sparse moe upcycle urls: - https://huggingface.co/bartowski/phi3-4x4b-v1-GGUF - https://huggingface.co/Fizzarolli/phi3-4x4b-v1 overrides: parameters: model: phi3-4x4b-v1-Q4_K_M.gguf files: - filename: phi3-4x4b-v1-Q4_K_M.gguf uri: huggingface://bartowski/phi3-4x4b-v1-GGUF/phi3-4x4b-v1-Q4_K_M.gguf sha256: fd33220186b7076f4b306f27b3a8913384435a2ca90185a71c9df5a752d3a298 - &hermes-2-pro-mistral ### START Hermes url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master" name: "hermes-2-pro-mistral" icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ggO2sBDJ8Bhc6w-zwTx5j.png license: apache-2.0 description: | Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house. This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 81% on our structured JSON Output evaluation. Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below. This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI Learn more about the function calling on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main urls: - https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF tags: - llm - gguf - gpu - mistral - cpu - function-calling overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q4_0.gguf files: - filename: "Hermes-2-Pro-Mistral-7B.Q4_0.gguf" sha256: "f446c3125026f7af6757dd097dda02280adc85e908c058bd6f1c41a118354745" uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q4_0.gguf" - !!merge <<: *hermes-2-pro-mistral name: "hermes-2-pro-mistral:Q6_K" overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q6_K.gguf files: - filename: "Hermes-2-Pro-Mistral-7B.Q6_K.gguf" sha256: "40adc3b227bc36764de148fdda4df5df385adc06650d58d4dbe726ee0214eeff" uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf" - !!merge <<: *hermes-2-pro-mistral name: "hermes-2-pro-mistral:Q8_0" overrides: parameters: model: Hermes-2-Pro-Mistral-7B.Q8_0.gguf files: - filename: "Hermes-2-Pro-Mistral-7B.Q8_0.gguf" sha256: "b6d95d7ec9a395b7568cc94b0447fd4f90b6f69d6e44794b1fbb84e3f732baca" uri: "huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q8_0.gguf" - !!merge <<: *hermes-2-pro-mistral name: "hermes-2-theta-llama-3-8b" icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/HQnQmNM1L3KXGhp0wUzHH.png tags: - llm - gguf - gpu - llama3 - cpu - function-calling description: | Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research, in collaboration with Charles Goddard at Arcee, the team behind MergeKit. Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model. urls: - https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF overrides: parameters: model: Hermes-2-Pro-Llama-3-Instruct-Merged-DPO-Q4_K_M.gguf files: - filename: "Hermes-2-Pro-Llama-3-Instruct-Merged-DPO-Q4_K_M.gguf" sha256: "762b9371a296ab2628592b9462dc676b27d881a3402816492801641a437669b3" uri: "huggingface://NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-Instruct-Merged-DPO-Q4_K_M.gguf" - !!merge <<: *hermes-2-pro-mistral name: "hermes-2-theta-llama-3-70b" icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/P4NxBFwfBbboNZVytpn45.png tags: - llm - gguf - gpu - llama3 - cpu - function-calling description: | Hermes-2 Θ (Theta) 70B is the continuation of our experimental merged model released by Nous Research, in collaboration with Charles Goddard and Arcee AI, the team behind MergeKit. Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model. urls: - https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF overrides: parameters: model: Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf files: - filename: "Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf" uri: "huggingface://NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF/Hermes-2-Theta-Llama-3-70B-Q4_K_M.gguf" sha256: b3965f671c35d09da8b903218f5bbaac94efdd9000e4fe4a2bac87fcac9f664e ### LLAMA3 version - !!merge <<: *hermes-2-pro-mistral name: "hermes-2-pro-llama-3-8b" tags: - llm - gguf - gpu - llama3 - function-calling - cpu urls: - https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF overrides: parameters: model: Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf files: - filename: "Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf" sha256: "10c52a4820137a35947927be741bb411a9200329367ce2590cc6757cd98e746c" uri: "huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf" - !!merge <<: *hermes-2-pro-mistral tags: - llm - gguf - gpu - llama3 - function-calling - cpu name: "hermes-2-pro-llama-3-8b:Q5_K_M" urls: - https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF overrides: parameters: model: Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf files: - filename: "Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf" sha256: "107f3f55e26b8cc144eadd83e5f8a60cfd61839c56088fa3ae2d5679abf45f29" uri: "huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf" - !!merge <<: *hermes-2-pro-mistral tags: - llm - gguf - gpu - function-calling - llama3 - cpu name: "hermes-2-pro-llama-3-8b:Q8_0" urls: - https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF overrides: parameters: model: Hermes-2-Pro-Llama-3-8B-Q8_0.gguf files: - filename: "Hermes-2-Pro-Llama-3-8B-Q8_0.gguf" sha256: "d138388cfda04d185a68eaf2396cf7a5cfa87d038a20896817a9b7cf1806f532" uri: "huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf" - !!merge <<: *hermes-2-pro-mistral name: "biomistral-7b" description: | BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains urls: - https://huggingface.co/MaziyarPanahi/BioMistral-7B-GGUF icon: https://huggingface.co/BioMistral/BioMistral-7B/resolve/main/wordart_blue_m_rectangle.png?download=true overrides: parameters: model: BioMistral-7B.Q4_K_M.gguf files: - filename: "BioMistral-7B.Q4_K_M.gguf" sha256: "3a73107045dfe7e3f113b392b0a67e3e6ca9fa9dae2abe301424ce5abd1721a6" uri: "huggingface://MaziyarPanahi/BioMistral-7B-GGUF/BioMistral-7B.Q4_K_M.gguf" - !!merge <<: *hermes-2-pro-mistral name: "tiamat-8b-1.2-llama-3-dpo" icon: https://huggingface.co/Gryphe/Tiamat-8b-1.2-Llama-3-DPO/resolve/main/Tiamat.png description: | Obligatory Disclaimer: Tiamat is not nice. Ever wanted to be treated disdainfully like the foolish mortal you are? Wait no more, for Tiamat is here to berate you! Hailing from the world of the Forgotten Realms, she will happily judge your every word. Tiamat was created with the following question in mind; Is it possible to create an assistant with strong anti-assistant personality traits? Try it yourself and tell me afterwards! She was fine-tuned on top of Nous Research's shiny new Hermes 2 Pro. urls: - https://huggingface.co/bartowski/Tiamat-8b-1.2-Llama-3-DPO-GGUF overrides: parameters: model: Tiamat-8b-1.2-Llama-3-DPO-Q4_K_M.gguf files: - filename: "Tiamat-8b-1.2-Llama-3-DPO-Q4_K_M.gguf" sha256: "7b0895d2183344b2ac1ff36b9f3fe31dd8d4cf8820c4a41ef74e50ef86e3b448" uri: "huggingface://bartowski/Tiamat-8b-1.2-Llama-3-DPO-GGUF/Tiamat-8b-1.2-Llama-3-DPO-Q4_K_M.gguf" - url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "guillaumetell-7b" license: apache-2 description: | Guillaume Tell est un Large Language Model (LLM) français basé sur Mistral Open-Hermes 2.5 optimisé pour le RAG (Retrieval Augmented Generation) avec traçabilité des sources et explicabilité. urls: - https://huggingface.co/MaziyarPanahi/guillaumetell-7b-GGUF - https://huggingface.co/AgentPublic/guillaumetell-7b tags: - llm - gguf - gpu - cpu - openhermes - french overrides: context_size: 4096 parameters: model: guillaumetell-7b.Q4_K_M.gguf files: - filename: guillaumetell-7b.Q4_K_M.gguf sha256: bf08db5281619335f3ee87e229c8533b04262790063b061bb8f275c3e4de7061 uri: huggingface://MaziyarPanahi/guillaumetell-7b-GGUF/guillaumetell-7b.Q4_K_M.gguf - !!merge <<: *hermes-2-pro-mistral name: "kunocchini-7b-128k-test-imatrix" description: | The following models were included in the merge: SanjiWatsuki/Kunoichi-DPO-v2-7B Epiculous/Fett-uccine-Long-Noodle-7B-120k-Contex urls: - https://huggingface.co/Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix icon: https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/9obNSalcJqCilQwr_4ssM.jpeg overrides: parameters: model: v2_Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf files: - filename: "v2_Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf" sha256: "5ccec35392f56f66952f8eb2ded2d8aa9a6bb511e9518899d8096326e328edef" uri: "huggingface://Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix/v2_Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf" ### START Cerbero - url: "github:mudler/LocalAI/gallery/cerbero.yaml@master" icon: https://huggingface.co/galatolo/cerbero-7b/resolve/main/README.md.d/cerbero.png description: | cerbero-7b is specifically crafted to fill the void in Italy's AI landscape. urls: - https://huggingface.co/galatolo/cerbero-7b tags: - llm - gguf - gpu - cpu - mistral - italian overrides: parameters: model: galatolo-Q4_K.gguf files: - filename: "galatolo-Q4_K.gguf" sha256: "ca0cfd5a9ad40dc16416aa3a277015d0299b62c0803b67f5709580042202c172" uri: "huggingface://galatolo/cerbero-7b-gguf/ggml-model-Q4_K.gguf" - &codellama ### START Codellama url: "github:mudler/LocalAI/gallery/codellama.yaml@master" name: "codellama-7b" license: llama2 description: | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This model is designed for general code synthesis and understanding. urls: - https://huggingface.co/TheBloke/CodeLlama-7B-GGUF - https://huggingface.co/meta-llama/CodeLlama-7b-hf tags: - llm - gguf - gpu - llama2 - cpu overrides: parameters: model: codellama-7b.Q4_0.gguf files: - filename: "codellama-7b.Q4_0.gguf" sha256: "33052f6dd41436db2f83bd48017b6fff8ce0184e15a8a227368b4230f1da97b5" uri: "huggingface://TheBloke/CodeLlama-7B-GGUF/codellama-7b.Q4_0.gguf" - !!merge <<: *codellama name: "codestral-22b-v0.1" license: mnpl description: | Codestral-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the Blogpost). The model can be queried: As instruct, for instance to answer any questions about a code snippet (write documentation, explain, factorize) or to generate code following specific indications As Fill in the Middle (FIM), to predict the middle tokens between a prefix and a suffix (very useful for software development add-ons like in VS Code) urls: - https://huggingface.co/mistralai/Codestral-22B-v0.1 - https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF tags: - llm - gguf - gpu - code - cpu overrides: parameters: model: Codestral-22B-v0.1-Q4_K_M.gguf files: - filename: "Codestral-22B-v0.1-Q4_K_M.gguf" uri: "huggingface://bartowski/Codestral-22B-v0.1-GGUF/Codestral-22B-v0.1-Q4_K_M.gguf" sha256: 003e48ed892850b80994fcddca2bd6b833b092a4ef2db2853c33a3144245e06c - &llm-compiler url: "github:mudler/LocalAI/gallery/codellama.yaml@master" name: "llm-compiler-13b-imat" license: other description: | LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. LLM Compiler is free for both research and commercial use. LLM Compiler is available in two flavors: LLM Compiler, the foundational models, pretrained on over 500B tokens of LLVM-IR, x86_84, ARM, and CUDA assembly codes and trained to predict the effect of LLVM optimizations; and LLM Compiler FTD, which is further fine-tuned to predict the best optimizations for code in LLVM assembly to reduce code size, and to disassemble assembly code to LLVM-IR. urls: - https://huggingface.co/legraphista/llm-compiler-13b-IMat-GGUF - https://huggingface.co/facebook/llm-compiler-13b tags: - llm - gguf - gpu - code - cpu overrides: parameters: model: llm-compiler-13b.Q4_K.gguf files: - filename: "llm-compiler-13b.Q4_K.gguf" uri: "huggingface://legraphista/llm-compiler-13b-IMat-GGUF/llm-compiler-13b.Q4_K.gguf" sha256: dad41a121d0d67432c289aba8ffffc93159e2b24ca3d1c62e118c9f4cbf0c890 - !!merge <<: *llm-compiler name: "llm-compiler-13b-ftd" urls: - https://huggingface.co/QuantFactory/llm-compiler-13b-ftd-GGUF - https://huggingface.co/facebook/llm-compiler-13b-ftd overrides: parameters: model: llm-compiler-13b-ftd.Q4_K_M.gguf files: - filename: "llm-compiler-13b-ftd.Q4_K_M.gguf" uri: "huggingface://QuantFactory/llm-compiler-13b-ftd-GGUF/llm-compiler-13b-ftd.Q4_K_M.gguf" sha256: a5d19ae6b3fbe6724784363161b66cd2c8d8a3905761c0fb08245b3c03697db1 - !!merge <<: *llm-compiler name: "llm-compiler-7b-imat-GGUF" urls: - https://huggingface.co/legraphista/llm-compiler-7b-IMat-GGUF - https://huggingface.co/facebook/llm-compiler-7b overrides: parameters: model: llm-compiler-7b.Q4_K.gguf files: - filename: "llm-compiler-7b.Q4_K.gguf" uri: "huggingface://legraphista/llm-compiler-7b-IMat-GGUF/llm-compiler-7b.Q4_K.gguf" sha256: 84926979701fa4591ff5ede94a6c5829a62efa620590e5815af984707d446926 - !!merge <<: *llm-compiler name: "llm-compiler-7b-ftd-imat" urls: - https://huggingface.co/legraphista/llm-compiler-7b-ftd-IMat-GGUF - https://huggingface.co/facebook/llm-compiler-7b-ftd overrides: parameters: model: llm-compiler-7b-ftd.Q4_K.gguf files: - filename: "llm-compiler-7b-ftd.Q4_K.gguf" uri: "huggingface://legraphista/llm-compiler-7b-ftd-IMat-GGUF/llm-compiler-7b-ftd.Q4_K.gguf" sha256: d862dd18ed335413787d0ad196522a9902a3c10a6456afdab8721822cb0ddde8 - &openvino ### START OpenVINO url: "github:mudler/LocalAI/gallery/openvino.yaml@master" name: "openvino-llama-3-8b-instruct-ov-int8" license: llama3 urls: - https://huggingface.co/fakezeta/llama-3-8b-instruct-ov-int8 overrides: parameters: model: fakezeta/llama-3-8b-instruct-ov-int8 stopwords: - "<|eot_id|>" - "<|end_of_text|>" tags: - llm - openvino - gpu - llama3 - cpu - !!merge <<: *openvino name: "openvino-phi3" urls: - https://huggingface.co/fakezeta/Phi-3-mini-128k-instruct-ov-int8 overrides: trust_remote_code: true context_size: 131072 parameters: model: fakezeta/Phi-3-mini-128k-instruct-ov-int8 stopwords: - <|end|> tags: - llm - openvino - gpu - phi3 - cpu - Remote Code Enabled - !!merge <<: *openvino icon: https://cdn-uploads.huggingface.co/production/uploads/62f7a16192950415b637e201/HMD6WEoqqrAV8Ng_fAcnN.png name: "openvino-llama3-aloe" urls: - https://huggingface.co/fakezeta/Llama3-Aloe-8B-Alpha-ov-int8 overrides: context_size: 8192 parameters: model: fakezeta/Llama3-Aloe-8B-Alpha-ov-int8 stopwords: - "<|eot_id|>" - "<|end_of_text|>" - !!merge <<: *openvino name: "openvino-starling-lm-7b-beta-openvino-int8" urls: - https://huggingface.co/fakezeta/Starling-LM-7B-beta-openvino-int8 overrides: context_size: 8192 parameters: model: fakezeta/Starling-LM-7B-beta-openvino-int8 tags: - llm - openvino - gpu - mistral - cpu - !!merge <<: *openvino name: "openvino-wizardlm2" urls: - https://huggingface.co/fakezeta/Not-WizardLM-2-7B-ov-int8 overrides: context_size: 8192 parameters: model: fakezeta/Not-WizardLM-2-7B-ov-int8 - !!merge <<: *openvino name: "openvino-hermes2pro-llama3" urls: - https://huggingface.co/fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 overrides: context_size: 8192 parameters: model: fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 tags: - llm - openvino - gpu - llama3 - cpu - !!merge <<: *openvino name: "openvino-multilingual-e5-base" urls: - https://huggingface.co/intfloat/multilingual-e5-base overrides: embeddings: true type: OVModelForFeatureExtraction parameters: model: intfloat/multilingual-e5-base tags: - llm - openvino - gpu - embedding - cpu - !!merge <<: *openvino name: "openvino-all-MiniLM-L6-v2" urls: - https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 overrides: embeddings: true type: OVModelForFeatureExtraction parameters: model: sentence-transformers/all-MiniLM-L6-v2 tags: - llm - openvino - gpu - embedding - cpu - &sentencentransformers ### START Embeddings description: | This framework provides an easy method to compute dense vector representations for sentences, paragraphs, and images. The models are based on transformer networks like BERT / RoBERTa / XLM-RoBERTa etc. and achieve state-of-the-art performance in various tasks. Text is embedded in vector space such that similar text are closer and can efficiently be found using cosine similarity. urls: - https://github.com/UKPLab/sentence-transformers tags: - gpu - cpu - embeddings - python name: "all-MiniLM-L6-v2" url: "github:mudler/LocalAI/gallery/sentencetransformers.yaml@master" overrides: parameters: model: all-MiniLM-L6-v2 - &dreamshaper ### START Image generation name: dreamshaper icon: https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/dd9b038c-bd15-43ab-86ab-66e145ad7ff2/width=450/26072158-132340247-8k%20portrait%20of%20beautiful%20cyborg%20with%20brown%20hair,%20intricate,%20elegant,%20highly%20detailed,%20majestic,%20digital%20photography,%20art%20by%20artg_ed.jpeg license: other description: | A text-to-image model that uses Stable Diffusion 1.5 to generate images from text prompts. This model is DreamShaper model by Lykon. urls: - https://civitai.com/models/4384/dreamshaper tags: - text-to-image - stablediffusion - python - sd-1.5 - gpu url: "github:mudler/LocalAI/gallery/dreamshaper.yaml@master" overrides: parameters: model: DreamShaper_8_pruned.safetensors files: - filename: DreamShaper_8_pruned.safetensors uri: huggingface://Lykon/DreamShaper/DreamShaper_8_pruned.safetensors sha256: 879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd - name: stable-diffusion-3-medium icon: https://huggingface.co/leo009/stable-diffusion-3-medium/resolve/main/sd3demo.jpg license: other description: | Stable Diffusion 3 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. urls: - https://huggingface.co/stabilityai/stable-diffusion-3-medium - https://huggingface.co/leo009/stable-diffusion-3-medium tags: - text-to-image - stablediffusion - python - sd-3 - gpu url: "github:mudler/LocalAI/gallery/stablediffusion3.yaml@master" - &whisper ## Whisper url: "github:mudler/LocalAI/gallery/whisper-base.yaml@master" name: "whisper-1" license: "MIT" urls: - https://github.com/ggerganov/whisper.cpp - https://huggingface.co/ggerganov/whisper.cpp overrides: parameters: model: ggml-whisper-base.bin files: - filename: "ggml-whisper-base.bin" sha256: "60ed5bc3dd14eea856493d334349b405782ddcaf0028d4b5df4088345fba2efe" uri: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" description: | Port of OpenAI's Whisper model in C/C++ - !!merge <<: *whisper name: "whisper-base-q5_1" overrides: parameters: model: ggml-model-whisper-base-q5_1.bin files: - filename: "ggml-model-whisper-base-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-base-q5_1.bin" sha256: 422f1ae452ade6f30a004d7e5c6a43195e4433bc370bf23fac9cc591f01a8898 - !!merge <<: *whisper name: "whisper-base" overrides: parameters: model: ggml-model-whisper-base.bin files: - filename: "ggml-model-whisper-base.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-base.bin" sha256: 60ed5bc3dd14eea856493d334349b405782ddcaf0028d4b5df4088345fba2efe - !!merge <<: *whisper name: "whisper-base-en-q5_1" overrides: parameters: model: ggml-model-whisper-base.en-q5_1.bin files: - filename: "ggml-model-whisper-base.en-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-base.en-q5_1.bin" sha256: 4baf70dd0d7c4247ba2b81fafd9c01005ac77c2f9ef064e00dcf195d0e2fdd2f - !!merge <<: *whisper name: "whisper-base-en" overrides: parameters: model: ggml-model-whisper-base.en.bin files: - filename: "ggml-model-whisper-base.en.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-base.en.bin" sha256: a03779c86df3323075f5e796cb2ce5029f00ec8869eee3fdfb897afe36c6d002 - !!merge <<: *whisper name: "whisper-large-q5_0" overrides: parameters: model: ggml-model-whisper-large-q5_0.bin files: - filename: "ggml-model-whisper-large-q5_0.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-large-q5_0.bin" sha256: 3a214837221e4530dbc1fe8d734f302af393eb30bd0ed046042ebf4baf70f6f2 - !!merge <<: *whisper name: "whisper-medium-q5_0" overrides: parameters: model: ggml-model-whisper-medium-q5_0.bin files: - filename: "ggml-model-whisper-medium-q5_0.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-medium-q5_0.bin" sha256: 19fea4b380c3a618ec4723c3eef2eb785ffba0d0538cf43f8f235e7b3b34220f - !!merge <<: *whisper name: "whisper-small-q5_1" overrides: parameters: model: ggml-model-whisper-small-q5_1.bin files: - filename: "ggml-model-whisper-small-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-small-q5_1.bin" sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb - !!merge <<: *whisper name: "whisper-small" overrides: parameters: model: ggml-model-whisper-small.bin files: - filename: "ggml-model-whisper-small.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-small.bin" sha256: 1be3a9b2063867b937e64e2ec7483364a79917e157fa98c5d94b5c1fffea987b - !!merge <<: *whisper name: "whisper-small-en-q5_1" overrides: parameters: model: ggml-model-whisper-small.en-q5_1.bin files: - filename: "ggml-model-whisper-small.en-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-small.en-q5_1.bin" sha256: bfdff4894dcb76bbf647d56263ea2a96645423f1669176f4844a1bf8e478ad30 - !!merge <<: *whisper name: "whisper-small" overrides: parameters: model: ggml-model-whisper-small.en.bin files: - filename: "ggml-model-whisper-small.en.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-small.en.bin" sha256: c6138d6d58ecc8322097e0f987c32f1be8bb0a18532a3f88f734d1bbf9c41e5d - !!merge <<: *whisper name: "whisper-small-q5_1" overrides: parameters: model: ggml-model-whisper-small-q5_1.bin files: - filename: "ggml-model-whisper-small-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-small-q5_1.bin" sha256: ae85e4a935d7a567bd102fe55afc16bb595bdb618e11b2fc7591bc08120411bb - !!merge <<: *whisper name: "whisper-tiny" overrides: parameters: model: ggml-model-whisper-tiny.bin files: - filename: "ggml-model-whisper-tiny.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-tiny.bin" sha256: be07e048e1e599ad46341c8d2a135645097a538221678b7acdd1b1919c6e1b21 - !!merge <<: *whisper name: "whisper-tiny-q5_1" overrides: parameters: model: ggml-model-whisper-tiny-q5_1.bin files: - filename: "ggml-model-whisper-tiny-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-tiny-q5_1.bin" sha256: 818710568da3ca15689e31a743197b520007872ff9576237bda97bd1b469c3d7 - !!merge <<: *whisper name: "whisper-tiny-en-q5_1" overrides: parameters: model: ggml-model-whisper-tiny.en-q5_1.bin files: - filename: "ggml-model-whisper-tiny.en-q5_1.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-tiny.en-q5_1.bin" sha256: c77c5766f1cef09b6b7d47f21b546cbddd4157886b3b5d6d4f709e91e66c7c2b - !!merge <<: *whisper name: "whisper-tiny-en" overrides: parameters: model: ggml-model-whisper-tiny.en.bin files: - filename: "ggml-model-whisper-tiny.en.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-tiny.en.bin" sha256: 921e4cf8686fdd993dcd081a5da5b6c365bfde1162e72b08d75ac75289920b1f - !!merge <<: *whisper name: "whisper-tiny-en-q8_0" overrides: parameters: model: ggml-model-whisper-tiny.en-q8_0.bin files: - filename: "ggml-model-whisper-tiny.en-q8_0.bin" uri: "https://ggml.ggerganov.com/ggml-model-whisper-tiny.en-q8_0.bin" sha256: 5bc2b3860aa151a4c6e7bb095e1fcce7cf12c7b020ca08dcec0c6d018bb7dd94 ## Bert embeddings - url: "github:mudler/LocalAI/gallery/bert-embeddings.yaml@master" name: "bert-embeddings" license: "Apache 2.0" urls: - https://huggingface.co/skeskinen/ggml tags: - embeddings description: | Bert model that can be used for embeddings ## Stable Diffusion - url: github:mudler/LocalAI/gallery/stablediffusion.yaml@master license: "BSD-3" urls: - https://github.com/EdVince/Stable-Diffusion-NCNN - https://github.com/EdVince/Stable-Diffusion-NCNN/blob/main/LICENSE description: | Stable Diffusion in NCNN with c++, supported txt2img and img2img name: stablediffusion-cpp ## Tiny Dream - url: github:mudler/LocalAI/gallery/tinydream.yaml@master name: tinydream license: "BSD-3" urls: - https://github.com/symisc/tiny-dream - https://github.com/symisc/tiny-dream/blob/main/LICENSE description: | An embedded, Header Only, Stable Diffusion C++ implementation - &piper ## Piper TTS url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-kathleen-low icon: https://github.com/rhasspy/piper/raw/master/etc/logo.png license: mit urls: - https://github.com/rhasspy/piper description: | A fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. Piper is used in a variety of [projects](https://github.com/rhasspy/piper#people-using-piper). tags: - tts - text-to-speech - cpu overrides: parameters: model: en-us-kathleen-low.onnx files: - filename: voice-en-us-kathleen-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-kathleen-low.tar.gz sha256: 18e32f009f864d8061af8a4be4ae9018b5aa8b49c37f9e108bbfd782c6a38fbf - !!merge <<: *piper name: voice-ca-upc_ona-x-low overrides: parameters: model: ca-upc_ona-x-low.onnx files: - filename: voice-ca-upc_ona-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-ca-upc_ona-x-low.tar.gz sha256: c750d3f6ad35c8d95d5b0d1ad30ede2525524e48390f70a0871bdb7980cc271e - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ca-upc_pau-x-low overrides: parameters: model: ca-upc_pau-x-low.onnx files: - filename: voice-ca-upc_pau-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-ca-upc_pau-x-low.tar.gz sha256: 13c658ecd46a2dbd9dadadf7100623e53106239afcc359f9e27511b91e642f1f - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-da-nst_talesyntese-medium overrides: parameters: model: da-nst_talesyntese-medium.onnx files: - filename: voice-da-nst_talesyntese-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-da-nst_talesyntese-medium.tar.gz sha256: 1bdf673b946a2ba69fab24ae3fc0e7d23e042c2533cbbef008f64f633500eb7e - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-eva_k-x-low overrides: parameters: model: de-eva_k-x-low.onnx files: - filename: voice-de-eva_k-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-eva_k-x-low.tar.gz sha256: 81b305abc58a0a02629aea01904a86ec97b823714dd66b1ee22f38fe529e6371 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-karlsson-low overrides: parameters: model: de-karlsson-low.onnx files: - filename: voice-de-karlsson-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-karlsson-low.tar.gz sha256: cc7615cfef3ee6beaa1db6059e0271e4d2e1d6d310c0e17b3d36c494628f4b82 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-kerstin-low overrides: parameters: model: de-kerstin-low.onnx files: - filename: voice-de-kerstin-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-kerstin-low.tar.gz sha256: d8ea72fbc0c21db828e901777ba7bb5dff7c843bb943ad19f34c9700b96a8182 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-pavoque-low overrides: parameters: model: de-pavoque-low.onnx files: - filename: voice-de-pavoque-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-pavoque-low.tar.gz sha256: 1f5ebc6398e8829f19c7c2b14f46307703bca0f0d8c74b4bb173037b1f161d4d - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-ramona-low overrides: parameters: model: de-ramona-low.onnx files: - filename: voice-de-ramona-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-ramona-low.tar.gz sha256: 66d9fc08d1a1c537a1cefe99a284f687e5ad7e43d5935a75390678331cce7b47 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-de-thorsten-low overrides: parameters: model: de-thorsten-low.onnx files: - filename: voice-de-thorsten-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-de-thorsten-low.tar.gz sha256: 4d052a7726b77719d0dbc66c845f1d0fe4432bfbd26f878f6dd0883d49e9e43d - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-el-gr-rapunzelina-low overrides: parameters: model: el-gr-rapunzelina-low.onnx files: - filename: voice-el-gr-rapunzelina-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-el-gr-rapunzelina-low.tar.gz sha256: c5613688c12eabc5294465494ed56af1e0fe4d7896d216bfa470eb225d9ff0d0 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-gb-alan-low overrides: parameters: model: en-gb-alan-low.onnx files: - filename: voice-en-gb-alan-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-gb-alan-low.tar.gz sha256: 526eeeeccb26206dc92de5965615803b5bf88df059f46372caa4a9fa12d76a32 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-gb-southern_english_female-low overrides: parameters: model: en-gb-southern_english files: - filename: voice-en-gb-southern_english_female-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-gb-southern_english_female-low.tar.gz sha256: 7c1bbe23e61a57bdb450b137f69a83ff5358159262e1ed7d2308fa14f4924da9 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-amy-low overrides: parameters: model: en-us-amy-low.onnx files: - filename: voice-en-us-amy-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-amy-low.tar.gz sha256: 5c3e3480e7d71ce219943c8a711bb9c21fd48b8f8e87ed7fb5c6649135ab7608 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-danny-low overrides: parameters: model: en-us-danny-low.onnx files: - filename: voice-en-us-danny-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-danny-low.tar.gz sha256: 0c8fbb42526d5fbd3a0bded5f18041c0a893a70a7fb8756f97866624b932264b - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-kathleen-low overrides: parameters: model: en-us-kathleen-low.onnx files: - filename: voice-en-us-kathleen-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-kathleen-low.tar.gz sha256: 18e32f009f864d8061af8a4be4ae9018b5aa8b49c37f9e108bbfd782c6a38fbf - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-lessac-low overrides: parameters: model: en-us-lessac-low.onnx files: - filename: voice-en-us-lessac-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-lessac-low.tar.gz sha256: 003fe040985d00b917ace21b2ccca344c282c53fe9b946991b7b0da52516e1fc - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-lessac-medium overrides: parameters: model: en-us-lessac-medium.onnx files: - filename: voice-en-us-lessac-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-lessac-medium.tar.gz sha256: d45ca50084c0558eb9581cd7d26938043bc8853513da47c63b94d95a2367a5c9 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-libritts-high overrides: parameters: model: en-us-libritts-high.onnx files: - filename: voice-en-us-libritts-high.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-libritts-high.tar.gz sha256: 328e3e9cb573a43a6c5e1aeca386e971232bdb1418a74d4674cf726c973a0ea8 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-high overrides: parameters: model: en-us-ryan-high.onnx files: - filename: voice-en-us-ryan-high.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-ryan-high.tar.gz sha256: de346b054703a190782f49acb9b93c50678a884fede49cfd85429d204802d678 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-low overrides: parameters: model: en-us-ryan-low.onnx files: - filename: voice-en-us-ryan-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-ryan-low.tar.gz sha256: 049e6e5bad07870fb1d25ecde97bac00f9c95c90589b2fef4b0fbf23c88770ce - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us-ryan-medium overrides: parameters: model: en-us-ryan-medium.onnx files: - filename: voice-en-us-ryan-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us-ryan-medium.tar.gz sha256: 2e00d747eaed6ce9f63f4991921ef3bb2bbfbc7f28cde4f14eb7048960f928d8 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-en-us_lessac overrides: parameters: model: en-us-lessac.onnx files: - filename: voice-en-us_lessac.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-en-us_lessac.tar.gz sha256: 0967af67fb0435aa509b0b794c0cb2cc57817ae8a5bff28cb8cd89ab6f5dcc3d - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-es-carlfm-x-low overrides: parameters: model: es-carlfm-x-low.onnx files: - filename: voice-es-carlfm-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-es-carlfm-x-low.tar.gz sha256: 0156a186de321639e6295521f667758ad086bc8433f0a6797a9f044ed5cf5bf3 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-es-mls_10246-low overrides: parameters: model: es-mls_10246-low.onnx files: - filename: voice-es-mls_10246-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-es-mls_10246-low.tar.gz sha256: ff1fe3fc2ab91e32acd4fa8cb92048e3cff0e20079b9d81324f01cd2dea50598 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-es-mls_9972-low overrides: parameters: model: es-mls_9972-low.onnx files: - filename: voice-es-mls_9972-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-es-mls_9972-low.tar.gz sha256: d95def9adea97a6a3fee7645d1167e00fb4fd60f8ce9bc3ebf1acaa9e3f455dc - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fi-harri-low overrides: parameters: model: fi-harri-low.onnx files: - filename: voice-fi-harri-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-fi-harri-low.tar.gz sha256: 4f1aaf00927d0eb25bf4fc5ef8be2f042e048593864ac263ee7b49c516832b22 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-gilles-low overrides: parameters: model: fr-gilles-low.onnx files: - filename: voice-fr-gilles-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-fr-gilles-low.tar.gz sha256: 77662c7332c2a6f522ab478287d9b0fe9afc11a2da71f310bf923124ee699aae - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-mls_1840-low overrides: parameters: model: fr-mls_1840-low.onnx files: - filename: voice-fr-mls_1840-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-fr-mls_1840-low.tar.gz sha256: 69169d1fac99a733112c08c7caabf457055990590a32ee83ebcada37f86132d3 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-siwis-low overrides: parameters: model: fr-siwis-low.onnx files: - filename: voice-fr-siwis-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-fr-siwis-low.tar.gz sha256: d3db8d47053e9b4108e1c1d29d5ea2b5b1a152183616c3134c222110ccde20f2 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-fr-siwis-medium overrides: parameters: model: fr-siwis-medium.onnx files: - filename: voice-fr-siwis-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-fr-siwis-medium.tar.gz sha256: 0c9ecdf9ecac6de4a46be85a162bffe0db7145bd3a4175831cea6cab4b41eefd - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-bui-medium overrides: parameters: model: is-bui-medium.onnx files: - filename: voice-is-bui-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-is-bui-medium.tar.gz sha256: e89ef01051cb48ca2a32338ed8749a4c966b912bb572c61d6d21f2d3822e505f - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-salka-medium overrides: parameters: model: is-salka-medium.onnx files: - filename: voice-is-salka-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-is-salka-medium.tar.gz sha256: 75923d7d6b4125166ca58ec82b5d23879012844483b428db9911e034e6626384 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-steinn-medium overrides: parameters: model: is-steinn-medium.onnx files: - filename: voice-is-steinn-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-is-steinn-medium.tar.gz sha256: 5a01a8df796f86fdfe12cc32a3412ebd83670d47708d94d926ba5ed0776e6dc9 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-is-ugla-medium overrides: parameters: model: is-ugla-medium.onnx files: - filename: voice-is-ugla-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-is-ugla-medium.tar.gz sha256: 501cd0376f7fd397f394856b7b3d899da4cc40a63e11912258b74da78af90547 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-it-riccardo_fasol-x-low overrides: parameters: model: it-riccardo_fasol-x-low.onnx files: - filename: voice-it-riccardo_fasol-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-it-riccardo_fasol-x-low.tar.gz sha256: 394b27b8780f5167e73a62ac103839cc438abc7edb544192f965e5b8f5f4acdb - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-iseke-x-low overrides: parameters: model: kk-iseke-x-low.onnx files: - filename: voice-kk-iseke-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-kk-iseke-x-low.tar.gz sha256: f434fffbea3e6d8cf392e44438a1f32a5d005fc93b41be84a6d663882ce7c074 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-issai-high overrides: parameters: model: kk-issai-high.onnx files: - filename: voice-kk-issai-high.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-kk-issai-high.tar.gz sha256: 84bf79d330d6cd68103e82d95bbcaa2628a99a565126dea94cea2be944ed4f32 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-kk-raya-x-low overrides: parameters: model: kk-raya-x-low.onnx files: - filename: voice-kk-raya-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-kk-raya-x-low.tar.gz sha256: 4cab4ce00c6f10450b668072d7980a2bc3ade3a39adee82e3ec4f519d4c57bd1 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ne-google-medium overrides: parameters: model: ne-google-medium.onnx files: - filename: voice-ne-google-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-ne-google-medium.tar.gz sha256: 0895b11a7a340baea37fb9c27fb50bc3fd0af9779085978277f962d236d3a7bd - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ne-google-x-low overrides: parameters: model: ne-google-x-low.onnx files: - filename: voice-ne-google-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-ne-google-x-low.tar.gz sha256: 870ba5718dfe3e478c6cce8a9a288b591b3575c750b57ffcd845e4ec64988f0b - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-mls_5809-low overrides: parameters: model: nl-mls_5809-low.onnx files: - filename: voice-nl-mls_5809-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-nl-mls_5809-low.tar.gz sha256: 398b9f0318dfe9d613cb066444efec0d8491905ae34cf502edb52030b75ef51c - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-mls_7432-low overrides: parameters: model: nl-mls_7432-low.onnx files: - filename: voice-nl-mls_7432-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-nl-mls_7432-low.tar.gz sha256: 0b3efc68ea7e735ba8f2e0a0f7e9b4b887b00f6530c02fca4aa69a6091adbe5e - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-nathalie-x-low overrides: parameters: model: nl-nathalie-x-low.onnx files: - filename: voice-nl-nathalie-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-nl-nathalie-x-low.tar.gz sha256: 2658d4fe2b791491780160216d187751f7c993aa261f3b8ec76dfcaf1ba74942 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-rdh-medium overrides: parameters: model: nl-rdh-medium.onnx files: - filename: voice-nl-rdh-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-nl-rdh-medium.tar.gz sha256: 16f74a195ecf13df1303fd85327532196cc1ecef2e72505200578fd410d0affb - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-nl-rdh-x-low overrides: parameters: model: nl-rdh-x-low.onnx files: - filename: voice-nl-rdh-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-nl-rdh-x-low.tar.gz sha256: 496363e5d6e080fd16ac5a1f9457c564b52f0ee8be7f2e2ba1dbf41ef0b23a39 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-no-talesyntese-medium overrides: parameters: model: no-talesyntese-medium.onnx files: - filename: voice-no-talesyntese-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-no-talesyntese-medium.tar.gz sha256: ed6b3593a0e70c90d52e225b85d7e0b805ad8e08482471bd2f73cf1404a6470d - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-pl-mls_6892-low overrides: parameters: model: pl-mls_6892-low.onnx files: - filename: voice-pl-mls_6892-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-pl-mls_6892-low.tar.gz sha256: 5361fcf586b1285025a2ccb8b7500e07c9d66fa8126ef518709c0055c4c0d6f4 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-pt-br-edresson-low overrides: parameters: model: pt-br-edresson-low.onnx files: - filename: voice-pt-br-edresson-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-pt-br-edresson-low.tar.gz sha256: c68be522a526e77f49e90eeb4c13c01b4acdfeb635759f0eeb0eea8f16fd1f33 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-ru-irinia-medium overrides: parameters: model: ru-irinia-medium.onnx files: - filename: voice-ru-irinia-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-ru-irinia-medium.tar.gz sha256: 897b62f170faee38f21d0bc36411164166ae351977e898b6cf33f6206890b55f - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-sv-se-nst-medium overrides: parameters: model: sv-se-nst-medium.onnx files: - filename: voice-sv-se-nst-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-sv-se-nst-medium.tar.gz sha256: 0d6cf357d55860162bf1bdd76bd4f0c396ff547e941bfb25df799d6f1866fda9 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-uk-lada-x-low overrides: parameters: model: uk-lada-x-low.onnx files: - filename: voice-uk-lada-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-uk-lada-x-low.tar.gz sha256: ff50acbd659fc226b57632acb1cee310009821ec44b4bc517effdd9827d8296b - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-vi-25hours-single-low overrides: parameters: model: vi-25hours-single-low.onnx files: - filename: voice-vi-25hours-single-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-vi-25hours-single-low.tar.gz sha256: 97e34d1b69dc7000a4ec3269f84339ed35905b3c9800a63da5d39b7649e4a666 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-vi-vivos-x-low overrides: parameters: model: vi-vivos-x-low.onnx files: - filename: voice-vi-vivos-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-vi-vivos-x-low.tar.gz sha256: 07cd4ca6438ec224012f7033eec1a2038724b78e4aa2bedf85f756656b52e1a7 - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-zh-cn-huayan-x-low overrides: parameters: model: zh-cn-huayan-x-low.onnx files: - filename: voice-zh-cn-huayan-x-low.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-zh-cn-huayan-x-low.tar.gz sha256: 609db0da8ee75beb2f17ce53c55abdbc8c0e04135482efedf1798b1938bf90fa - !!merge <<: *piper url: github:mudler/LocalAI/gallery/piper.yaml@master name: voice-zh_CN-huayan-medium overrides: parameters: model: zh_CN-huayan-medium.onnx files: - filename: voice-zh_CN-huayan-medium.tar.gz uri: https://github.com/rhasspy/piper/releases/download/v0.0.2/voice-zh_CN-huayan-medium.tar.gz sha256: 0299a5e7f481ba853404e9f0e1515a94d5409585d76963fa4d30c64bd630aa99