commit a0e4bc4128f7cf592c14c4d41d3be0029694b24e Author: ModelHub XC Date: Thu Jun 25 03:20:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..747de33 --- /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 +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.f16.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +STAIR-Qwen2-7B-DPO-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae67daf --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: thu-ml/STAIR-Qwen2-7B-DPO-3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +- arxiv:2502.02384 +--- +## About + + + + + + +static quants of https://huggingface.co/thu-ml/STAIR-Qwen2-7B-DPO-3 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/STAIR-Qwen2-7B-DPO-3-GGUF/resolve/main/STAIR-Qwen2-7B-DPO-3.f16.gguf) | f16 | 15.3 | 16 bpw, overkill | + +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. + + diff --git a/STAIR-Qwen2-7B-DPO-3.IQ4_XS.gguf b/STAIR-Qwen2-7B-DPO-3.IQ4_XS.gguf new file mode 100644 index 0000000..847a10d --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d372aa82c1468a95e95a9dc980acdef24797f2b6cfaec0556499f223ce9df75 +size 4250296512 diff --git a/STAIR-Qwen2-7B-DPO-3.Q2_K.gguf b/STAIR-Qwen2-7B-DPO-3.Q2_K.gguf new file mode 100644 index 0000000..6b18899 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b27dad72b56893ba7105ad5b12a3a15fe3eb1334d1b08c77c101d12fc676fee +size 3015938240 diff --git a/STAIR-Qwen2-7B-DPO-3.Q3_K_L.gguf b/STAIR-Qwen2-7B-DPO-3.Q3_K_L.gguf new file mode 100644 index 0000000..1a89c55 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822f07e1ac9d7f444b9075588c2f8166e3806b83c58a00247edbc8652b0521b7 +size 4088457408 diff --git a/STAIR-Qwen2-7B-DPO-3.Q3_K_M.gguf b/STAIR-Qwen2-7B-DPO-3.Q3_K_M.gguf new file mode 100644 index 0000000..7d5976c --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df63873316731d6896a9155775b7bb2d15a2cee8ca4db0c8c65ebe29276de6d3 +size 3808389312 diff --git a/STAIR-Qwen2-7B-DPO-3.Q3_K_S.gguf b/STAIR-Qwen2-7B-DPO-3.Q3_K_S.gguf new file mode 100644 index 0000000..4b6c015 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714f643abdfa452ad208c50a4a5d115e2699b1f9880c66ca538deec172c17bb9 +size 3492366528 diff --git a/STAIR-Qwen2-7B-DPO-3.Q4_K_M.gguf b/STAIR-Qwen2-7B-DPO-3.Q4_K_M.gguf new file mode 100644 index 0000000..0a6f757 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715c9422c13157dbda48bf590e1588b16d28f9c3c0bebe84752818d826142cb5 +size 4683071680 diff --git a/STAIR-Qwen2-7B-DPO-3.Q4_K_S.gguf b/STAIR-Qwen2-7B-DPO-3.Q4_K_S.gguf new file mode 100644 index 0000000..e4694f2 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b535ef650eb389008e232cbaaeb91a07e9e97946ee52ad6373efaa7118b97aec +size 4457767104 diff --git a/STAIR-Qwen2-7B-DPO-3.Q5_K_M.gguf b/STAIR-Qwen2-7B-DPO-3.Q5_K_M.gguf new file mode 100644 index 0000000..849e8c7 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2746495e0147190a00c708807f98530957ff83a7382b6c6554f363fe905312e +size 5444829376 diff --git a/STAIR-Qwen2-7B-DPO-3.Q5_K_S.gguf b/STAIR-Qwen2-7B-DPO-3.Q5_K_S.gguf new file mode 100644 index 0000000..8b25053 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea742986bb1783a94b045cc50cbf26ce14fb44e55a88cb55b14355b9d7d1073 +size 5315174592 diff --git a/STAIR-Qwen2-7B-DPO-3.Q6_K.gguf b/STAIR-Qwen2-7B-DPO-3.Q6_K.gguf new file mode 100644 index 0000000..20ce29f --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50556dd2b0c9af72a12a86e2e608703939fb3fc775576a2b6c007e17cdd8bc7e +size 6254196928 diff --git a/STAIR-Qwen2-7B-DPO-3.Q8_0.gguf b/STAIR-Qwen2-7B-DPO-3.Q8_0.gguf new file mode 100644 index 0000000..c82cdab --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9508087be22414cd0a9b8eab50de97313c0fa7f26198ff2f568a85e784551fc6 +size 8098523328 diff --git a/STAIR-Qwen2-7B-DPO-3.f16.gguf b/STAIR-Qwen2-7B-DPO-3.f16.gguf new file mode 100644 index 0000000..082da77 --- /dev/null +++ b/STAIR-Qwen2-7B-DPO-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff13d4cb4fe6a091942e2da7616cfc6cc63cf975111bde1bdabf2e7fc1d06326 +size 15237851328