commit 7096b6472634a772b4728c5dd2b3f2353234e815 Author: ModelHub XC Date: Thu Jul 23 08:30:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0bf4e5e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.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 + +Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF_imatrix.dat b/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF_imatrix.dat new file mode 100644 index 0000000..751752f Binary files /dev/null and b/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF_imatrix.dat differ diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_M.gguf new file mode 100644 index 0000000..8a163ba --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:746a3e4681e921a7a9148c51270b78e06e6794a03e2abbcb70f5d98f6c4739f8 +size 420211040 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_S.gguf new file mode 100644 index 0000000..8803f2c --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2032d355ad4236006da77c95d8c354ba905b820dbf358c5f5e214d3b0a5a2288 +size 412835168 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.Q6_K.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.Q6_K.gguf new file mode 100644 index 0000000..cae483f --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce84c7aacdf753dc7df57a3e51d5f65b31c1fb2d1cd6710b70aa0eb2e58b470 +size 505861472 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.Q8_0.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.Q8_0.gguf new file mode 100644 index 0000000..e015947 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24f8214af7d265d4b2017c95d2a82576e6906c5c8544984f89ed4aeadcecbc2 +size 531193184 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.fp16.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.fp16.gguf new file mode 100644 index 0000000..57380cb --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c03f27591b7a2cda2300185936c5130e8e15b33023c96b7a17f35660f0b0a123 +size 994389120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d241693 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft +inference: false +model_creator: tugstugi +model_name: Qwen2.5-Coder-0.5B-QwQ-draft-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/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF) +- Model creator: [tugstugi](https://huggingface.co/tugstugi) +- Original model: [tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft](https://huggingface.co/tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft) + +## Description +[MaziyarPanahi/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF) contains GGUF format model files for [tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft](https://huggingface.co/tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft). + +### 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