From 8bbf09370cebec062141c95fac9c4791d7029c28 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 16 Aug 2024 00:02:21 +0200 Subject: [PATCH] models(gallery): add hermes-3 (#3252) Signed-off-by: Ettore Di Giacinto --- gallery/hermes-2-pro-mistral.yaml | 1 - gallery/index.yaml | 30 ++++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/gallery/hermes-2-pro-mistral.yaml b/gallery/hermes-2-pro-mistral.yaml index 6ef42db7..22a5fb3a 100644 --- a/gallery/hermes-2-pro-mistral.yaml +++ b/gallery/hermes-2-pro-mistral.yaml @@ -11,7 +11,6 @@ config_file: | - "<|end_of_text|>" function: disable_no_action: true - return_name_in_function_response: true grammar: # Uncomment the line below to enable grammar matching for JSON results if the model is breaking # the output. This will make the model more accurate and won't break the JSON output. diff --git a/gallery/index.yaml b/gallery/index.yaml index 26ed6062..28ad036a 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -4604,6 +4604,36 @@ - 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: "hermes-3-llama-3.1-8b" + icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/bMcZ3sNNQK8SRZpHXBmwM.jpeg + urls: + - https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B + - https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF + description: | + Hermes 3 is a generalist language model developed by Nous Research. It is an advanced agentic model with improved roleplaying, reasoning, multi-turn conversation, long context coherence, and generalist assistant capabilities. The model is built on top of the Llama-3 architecture and has been fine-tuned to achieve superior performance in various tasks. It is designed to be a powerful and reliable tool for solving complex problems and assisting users in achieving their goals. Hermes 3 can be used for a wide range of applications, including research, education, and personal assistant tasks. It is available on the Hugging Face model hub for easy access and integration into existing workflows. + overrides: + parameters: + model: Hermes-3-Llama-3.1-8B.Q4_K_M.gguf + files: + - filename: Hermes-3-Llama-3.1-8B.Q4_K_M.gguf + sha256: d4403ce5a6e930f4c2509456388c20d633a15ff08dd52ef3b142ff1810ec3553 + uri: huggingface://NousResearch/Hermes-3-Llama-3.1-8B-GGUF/Hermes-3-Llama-3.1-8B.Q4_K_M.gguf +- !!merge <<: *hermes-2-pro-mistral + name: "hermes-3-llama-3.1-70b" + icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/vG6j5WxHX09yj32vgjJlI.jpeg + urls: + - https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B + - https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B-GGUF + description: | + Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board. It is designed to focus on aligning LLMs to the user, with powerful steering capabilities and control given to the end user. The model uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. It also supports function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills. + overrides: + parameters: + model: Hermes-3-Llama-3.1-70B.Q4_K_M.gguf + files: + - filename: Hermes-3-Llama-3.1-70B.Q4_K_M.gguf + sha256: 955c2f42caade4278f3c9dbffa32bb74572652b20e49e5340e782de3585bbe3f + uri: huggingface://NousResearch/Hermes-3-Llama-3.1-70B-GGUF/Hermes-3-Llama-3.1-70B.Q4_K_M.gguf - !!merge <<: *hermes-2-pro-mistral name: "biomistral-7b" description: |