mirror of
https://github.com/mudler/LocalAI.git
synced 2025-02-20 17:32:47 +00:00
chore(model-gallery): ⬆️ update checksum (#3675)
⬆️ Checksum updates in gallery/index.yaml
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
LocalAI [bot]
GitHub
parent
f2ba1cfb01
commit
4550abbfce
@ -59,8 +59,8 @@
|
||||
- filename: llama-3.2-1b-instruct-q8_0.gguf
|
||||
sha256: ba345c83bf5cc679c653b853c46517eea5a34f03ed2205449db77184d9ae62a9
|
||||
uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF/llama-3.2-1b-instruct-q8_0.gguf
|
||||
## Qwen2.5
|
||||
- &qwen25
|
||||
## Qwen2.5
|
||||
name: "qwen2.5-14b-instruct"
|
||||
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
||||
license: apache-2.0
|
||||
@ -89,11 +89,11 @@
|
||||
- https://huggingface.co/bartowski/Qwen2.5-Math-7B-Instruct-GGUF
|
||||
- https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct
|
||||
description: |
|
||||
In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical reward model Qwen2.5-Math-RM-72B.
|
||||
In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical reward model Qwen2.5-Math-RM-72B.
|
||||
|
||||
Unlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT.
|
||||
Unlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT.
|
||||
|
||||
The base models of Qwen2-Math are initialized with Qwen2-1.5B/7B/72B, and then pretrained on a meticulously designed Mathematics-specific Corpus. This corpus contains large-scale high-quality mathematical web texts, books, codes, exam questions, and mathematical pre-training data synthesized by Qwen2.
|
||||
The base models of Qwen2-Math are initialized with Qwen2-1.5B/7B/72B, and then pretrained on a meticulously designed Mathematics-specific Corpus. This corpus contains large-scale high-quality mathematical web texts, books, codes, exam questions, and mathematical pre-training data synthesized by Qwen2.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
|
||||
@ -195,8 +195,8 @@
|
||||
model: Qwen2.5-32B.Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Qwen2.5-32B.Q4_K_M.gguf
|
||||
sha256: 02703e27c8b964db445444581a6937ad7538f0c32a100b26b49fa0e8ff527155
|
||||
uri: huggingface://mradermacher/Qwen2.5-32B-GGUF/Qwen2.5-32B.Q4_K_M.gguf
|
||||
sha256: fa42a4067e3630929202b6bb1ef5cebc43c1898494aedfd567b7d53c7a9d84a6
|
||||
- !!merge <<: *qwen25
|
||||
name: "qwen2.5-32b-instruct"
|
||||
urls:
|
||||
@ -221,8 +221,8 @@
|
||||
- filename: Qwen2.5-72B-Instruct-Q4_K_M.gguf
|
||||
sha256: e4c8fad16946be8cf0bbf67eb8f4e18fc7415a5a6d2854b4cda453edb4082545
|
||||
uri: huggingface://bartowski/Qwen2.5-72B-Instruct-GGUF/Qwen2.5-72B-Instruct-Q4_K_M.gguf
|
||||
## SmolLM
|
||||
- &smollm
|
||||
## SmolLM
|
||||
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
||||
name: "smollm-1.7b-instruct"
|
||||
icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
|
||||
@ -651,9 +651,9 @@
|
||||
- https://huggingface.co/leafspark/Reflection-Llama-3.1-70B-bf16
|
||||
- https://huggingface.co/senseable/Reflection-Llama-3.1-70B-gguf
|
||||
description: |
|
||||
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
|
||||
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
|
||||
|
||||
The model was trained on synthetic data generated by Glaive. If you're training a model, Glaive is incredible — use them.
|
||||
The model was trained on synthetic data generated by Glaive. If you're training a model, Glaive is incredible — use them.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Reflection-Llama-3.1-70B-q4_k_m.gguf
|
||||
@ -973,15 +973,15 @@
|
||||
- https://huggingface.co/Sao10K/L3.1-8B-Niitama-v1.1
|
||||
- https://huggingface.co/Lewdiculous/L3.1-8B-Niitama-v1.1-GGUF-IQ-Imatrix
|
||||
description: |
|
||||
GGUF-IQ-Imatrix quants for Sao10K/L3.1-8B-Niitama-v1.1
|
||||
Here's the subjectively superior L3 version: L3-8B-Niitama-v1
|
||||
An experimental model using experimental methods.
|
||||
GGUF-IQ-Imatrix quants for Sao10K/L3.1-8B-Niitama-v1.1
|
||||
Here's the subjectively superior L3 version: L3-8B-Niitama-v1
|
||||
An experimental model using experimental methods.
|
||||
|
||||
More detail on it:
|
||||
More detail on it:
|
||||
|
||||
Tamamo and Niitama are made from the same data. Literally. The only thing that's changed is how theyre shuffled and formatted. Yet, I get wildly different results.
|
||||
Tamamo and Niitama are made from the same data. Literally. The only thing that's changed is how theyre shuffled and formatted. Yet, I get wildly different results.
|
||||
|
||||
Interesting, eh? Feels kinda not as good compared to the l3 version, but it's aight.
|
||||
Interesting, eh? Feels kinda not as good compared to the l3 version, but it's aight.
|
||||
overrides:
|
||||
parameters:
|
||||
model: L3.1-8B-Niitama-v1.1-Q4_K_M-imat.gguf
|
||||
@ -1606,8 +1606,8 @@
|
||||
urls:
|
||||
- https://huggingface.co/Lewdiculous/MN-12B-Lyra-v4-GGUF-IQ-Imatrix
|
||||
description: |
|
||||
A finetune of Mistral Nemo by Sao10K.
|
||||
Uses the ChatML prompt format.
|
||||
A finetune of Mistral Nemo by Sao10K.
|
||||
Uses the ChatML prompt format.
|
||||
overrides:
|
||||
parameters:
|
||||
model: MN-12B-Lyra-v4-Q4_K_M-imat.gguf
|
||||
@ -2134,7 +2134,7 @@
|
||||
- https://huggingface.co/EpistemeAI/Athena-codegemma-2-2b-it
|
||||
- https://huggingface.co/mradermacher/Athena-codegemma-2-2b-it-GGUF
|
||||
description: |
|
||||
Supervised fine tuned (sft unsloth) for coding with EpistemeAI coding dataset.
|
||||
Supervised fine tuned (sft unsloth) for coding with EpistemeAI coding dataset.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Athena-codegemma-2-2b-it.Q4_K_M.gguf
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user