commit c5f094c6e562758530d5cedd0c84295b3efae95a Author: ModelHub XC Date: Sat Jul 18 14:05:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +*.gguf* 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 \ No newline at end of file diff --git a/Qwen2.5-Coder-32B-YOYO.i1-IQ2_XS.gguf b/Qwen2.5-Coder-32B-YOYO.i1-IQ2_XS.gguf new file mode 100644 index 0000000..80e65f3 --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008cbb81fa0be6fe5bf05290c2f57ef1df3d744cbff508fe437439919b67f137 +size 9957551392 diff --git a/Qwen2.5-Coder-32B-YOYO.i1-IQ3_XS.gguf b/Qwen2.5-Coder-32B-YOYO.i1-IQ3_XS.gguf new file mode 100644 index 0000000..195ba19 --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0cd6855bdecdfb7657a0d6391b049812a6ade212a0125448c2be5cb712feaf +size 13705514272 diff --git a/Qwen2.5-Coder-32B-YOYO.i1-IQ4_XS.gguf b/Qwen2.5-Coder-32B-YOYO.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c642baa --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633c08f8fe2593519772530c176b3e98b833e07356319beb407a00fa6c7e9c1e +size 17693154592 diff --git a/Qwen2.5-Coder-32B-YOYO.i1-Q4_K_M.gguf b/Qwen2.5-Coder-32B-YOYO.i1-Q4_K_M.gguf new file mode 100644 index 0000000..075996d --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254c7aa5c573bd61b00f26c8c3dc31d1a8f4d781208b50fa3f9c0635d1d6c8e3 +size 19851336992 diff --git a/Qwen2.5-Coder-32B-YOYO.i1-Q5_K_M.gguf b/Qwen2.5-Coder-32B-YOYO.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ed34088 --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd26cc35b89c3edcc660bb435e389b68cceca2af53f71f47f7490de3faeaf88 +size 23262158112 diff --git a/Qwen2.5-Coder-32B-YOYO.i1-Q6_K.gguf b/Qwen2.5-Coder-32B-YOYO.i1-Q6_K.gguf new file mode 100644 index 0000000..f772bcd --- /dev/null +++ b/Qwen2.5-Coder-32B-YOYO.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101ca1ee198b8d6829d354848128cde8b24d35b11829b816919df7fbcb6bc80c +size 26886155552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a7e627 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: YOYO-AI/Qwen2.5-Coder-32B-YOYO +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/YOYO-AI/Qwen2.5-Coder-32B-YOYO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Coder-32B-YOYO-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-YOYO-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Qwen2.5-Coder-32B-YOYO-i1-GGUF/resolve/master/Qwen2.5-Coder-32B-YOYO.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + +