commit f7e72726efd702424c97a7bc7f178773294298c1 Author: ModelHub XC Date: Fri May 15 03:54:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..06c26d1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF_imatrix.dat b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF_imatrix.dat new file mode 100644 index 0000000..3e47d77 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d5eb7274bda2f0640111dc7bb7fd019c43cd5df68406057518d8d76667bebc +size 4988146 diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..df7c8bd --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72454d512795eec49e21cdeadc6221446f8a21b9c303be4f1bb2a9247856ca36 +size 5732999520 diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..688d7f5 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617d8dae4fdcf5e114dba6cbe35b3288a0a5efaf3ed0ecf9350638fea5b7611b +size 5599306080 diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q6_K.gguf b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..40465dd --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cb5d3d9ed24d7d75ec3c6b947f4c54ec632c8e614900f2084c7fca0992e83b +size 6596019072 diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q8_0.gguf b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..61b8568 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972afa916aa1ff5b67cf5b293ba9b9e7177647907ab18d8f61fa43032362dac7 +size 8540785472 diff --git a/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.fp16.gguf b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.fp16.gguf new file mode 100644 index 0000000..954feaf --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d0244e2ac087fe405e2a57797f56032574d345b7537f5de955d9b07ca6ed6e +size 16068913216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2904749 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: Broyojo/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning +inference: false +model_creator: Broyojo +model_name: Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +--- +# [MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF](https://huggingface.co/MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF) +- Model creator: [Broyojo](https://huggingface.co/Broyojo) +- Original model: [Broyojo/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning](https://huggingface.co/Broyojo/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning) + +## Description +[MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF](https://huggingface.co/MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning-GGUF) contains GGUF format model files for [Broyojo/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning](https://huggingface.co/Broyojo/Meta-Llama-3.1-8B-Instruct-PRM800K-Reasoning). + +### About GGUF + +GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. + +Here is an incomplete list of clients and libraries that are known to support GGUF: + +* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. +* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. +* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. +* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. +* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. +* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. +* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. +* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. +* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. +* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. + +## Special thanks + +🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..9f0f76f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "mistral" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file