From d0b3f8efc189d15dfcf66ce13d1f3e666e71481e Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 25 Aug 2026 13:29:14 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF Source: Original Platform --- .gitattributes | 65 ++++++++++++++++++++++++++++ Qwen2.5-3B-Instruct-GGUF_imatrix.dat | 3 ++ Qwen2.5-3B-Instruct.IQ1_M.gguf | 3 ++ Qwen2.5-3B-Instruct.IQ1_S.gguf | 3 ++ Qwen2.5-3B-Instruct.IQ2_XS.gguf | 3 ++ Qwen2.5-3B-Instruct.IQ3_XS.gguf | 3 ++ Qwen2.5-3B-Instruct.IQ4_XS.gguf | 3 ++ Qwen2.5-3B-Instruct.Q2_K.gguf | 3 ++ Qwen2.5-3B-Instruct.Q3_K_L.gguf | 3 ++ Qwen2.5-3B-Instruct.Q3_K_M.gguf | 3 ++ Qwen2.5-3B-Instruct.Q3_K_S.gguf | 3 ++ Qwen2.5-3B-Instruct.Q4_K_M.gguf | 3 ++ Qwen2.5-3B-Instruct.Q4_K_S.gguf | 3 ++ Qwen2.5-3B-Instruct.Q5_K_M.gguf | 3 ++ Qwen2.5-3B-Instruct.Q5_K_S.gguf | 3 ++ Qwen2.5-3B-Instruct.Q6_K.gguf | 3 ++ Qwen2.5-3B-Instruct.Q8_0.gguf | 3 ++ Qwen2.5-3B-Instruct.fp16.gguf | 3 ++ README.md | 46 ++++++++++++++++++++ config.json | 3 ++ configuration.json | 1 + 21 files changed, 166 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-3B-Instruct-GGUF_imatrix.dat create mode 100644 Qwen2.5-3B-Instruct.IQ1_M.gguf create mode 100644 Qwen2.5-3B-Instruct.IQ1_S.gguf create mode 100644 Qwen2.5-3B-Instruct.IQ2_XS.gguf create mode 100644 Qwen2.5-3B-Instruct.IQ3_XS.gguf create mode 100644 Qwen2.5-3B-Instruct.IQ4_XS.gguf create mode 100644 Qwen2.5-3B-Instruct.Q2_K.gguf create mode 100644 Qwen2.5-3B-Instruct.Q3_K_L.gguf create mode 100644 Qwen2.5-3B-Instruct.Q3_K_M.gguf create mode 100644 Qwen2.5-3B-Instruct.Q3_K_S.gguf create mode 100644 Qwen2.5-3B-Instruct.Q4_K_M.gguf create mode 100644 Qwen2.5-3B-Instruct.Q4_K_S.gguf create mode 100644 Qwen2.5-3B-Instruct.Q5_K_M.gguf create mode 100644 Qwen2.5-3B-Instruct.Q5_K_S.gguf create mode 100644 Qwen2.5-3B-Instruct.Q6_K.gguf create mode 100644 Qwen2.5-3B-Instruct.Q8_0.gguf create mode 100644 Qwen2.5-3B-Instruct.fp16.gguf create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..13801fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 + +Qwen2.5-3B-Instruct.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Qwen2.5-3B-Instruct-GGUF_imatrix.dat b/Qwen2.5-3B-Instruct-GGUF_imatrix.dat new file mode 100644 index 0000000..58b05d8 --- /dev/null +++ b/Qwen2.5-3B-Instruct-GGUF_imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851bf69b555f19410689c76946d363a204150e1515f5a7cd0743dd11e74e588e +size 3362966 diff --git a/Qwen2.5-3B-Instruct.IQ1_M.gguf b/Qwen2.5-3B-Instruct.IQ1_M.gguf new file mode 100644 index 0000000..6d07c6b --- /dev/null +++ b/Qwen2.5-3B-Instruct.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10034eff57f7da53a1bfe974b891d78a39ba8f57925cd318128d953f71d8452b +size 850027680 diff --git a/Qwen2.5-3B-Instruct.IQ1_S.gguf b/Qwen2.5-3B-Instruct.IQ1_S.gguf new file mode 100644 index 0000000..8562a71 --- /dev/null +++ b/Qwen2.5-3B-Instruct.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b24084e8f8004d080c9b3dba8fde810cbd7982a4492719145b3df1b51400e2 +size 791094432 diff --git a/Qwen2.5-3B-Instruct.IQ2_XS.gguf b/Qwen2.5-3B-Instruct.IQ2_XS.gguf new file mode 100644 index 0000000..5238588 --- /dev/null +++ b/Qwen2.5-3B-Instruct.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a82f01fd63d42570792d2bbb41088117aa0bee6ade11ad441881914444457a +size 1031546016 diff --git a/Qwen2.5-3B-Instruct.IQ3_XS.gguf b/Qwen2.5-3B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..4a21d84 --- /dev/null +++ b/Qwen2.5-3B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3699e8a2b62c378645fc1afde06e2f147d7afc8669ccf82ce6b9c57202250b6b +size 1391836320 diff --git a/Qwen2.5-3B-Instruct.IQ4_XS.gguf b/Qwen2.5-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..df0bf77 --- /dev/null +++ b/Qwen2.5-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e794ef49d36842e3d1702ab2d1adbfb8026631a82f46315c61534da55f8c6f3a +size 1739095200 diff --git a/Qwen2.5-3B-Instruct.Q2_K.gguf b/Qwen2.5-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6bf4aa8 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67ab712f7c83149769ff9f402e1bf4d95f8498fe0bcec546bd0127eff1ce4f7 +size 1274756256 diff --git a/Qwen2.5-3B-Instruct.Q3_K_L.gguf b/Qwen2.5-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9736571 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f72eb3dcd0332512371c349d52ce987df11f70f02380a513bf53d0fa2c99d2 +size 1707392160 diff --git a/Qwen2.5-3B-Instruct.Q3_K_M.gguf b/Qwen2.5-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..da17320 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3aabd22f21016aef2de3f8ce9aa1e207cf498463a5ef292061f08993482559 +size 1590475936 diff --git a/Qwen2.5-3B-Instruct.Q3_K_S.gguf b/Qwen2.5-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..0e86f61 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40dac85d0f2136abfbda6608223bcabe1624289b4bf72f6414ae6a3687734369 +size 1454357664 diff --git a/Qwen2.5-3B-Instruct.Q4_K_M.gguf b/Qwen2.5-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..a5a6f53 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7230acd716226852ed1bafad0b51137903a8924c798322e8dfb679315d78eae +size 1929903264 diff --git a/Qwen2.5-3B-Instruct.Q4_K_S.gguf b/Qwen2.5-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..db684ca --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b08ed008a55a94c66fe84baedf635c1e2bc26d72a8894ad37455e3949e3bccd +size 1834384544 diff --git a/Qwen2.5-3B-Instruct.Q5_K_M.gguf b/Qwen2.5-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..e4da817 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11dde20bd2c8bc4ea46baa69adaa0312f31df296e9ed13f37de04c5556bd6fa +size 2224815264 diff --git a/Qwen2.5-3B-Instruct.Q5_K_S.gguf b/Qwen2.5-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..47983b5 --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08df1bbffe78834acc2aad543d70314df8ed8fdb0595804074830a646d2d8725 +size 2169666720 diff --git a/Qwen2.5-3B-Instruct.Q6_K.gguf b/Qwen2.5-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..a4cf5ba --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195299941ed34cbfa658c84bb28e233ffd43ce62fb9b5c29304ba1ef39faad9f +size 2538159264 diff --git a/Qwen2.5-3B-Instruct.Q8_0.gguf b/Qwen2.5-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a7014bc --- /dev/null +++ b/Qwen2.5-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ed602236a167de033bc81c06f3cb5c7058e92b5900fbdd32efb6aa468c2709 +size 3285476512 diff --git a/Qwen2.5-3B-Instruct.fp16.gguf b/Qwen2.5-3B-Instruct.fp16.gguf new file mode 100644 index 0000000..df8f28b --- /dev/null +++ b/Qwen2.5-3B-Instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d5747748a796081d1284aedcc40ab6948d32deead23314ef06a5b77f2cb564c +size 6178317248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac00321 --- /dev/null +++ b/README.md @@ -0,0 +1,46 @@ +--- +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +- text-generation +model_name: Qwen2.5-3B-Instruct-GGUF +base_model: Qwen/Qwen2.5-3B-Instruct +inference: false +model_creator: Qwen +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +--- +# [MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF) +- Model creator: [Qwen](https://huggingface.co/Qwen) +- Original model: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) + +## Description +[MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF) contains GGUF format model files for [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct). + +### 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