commit f479f8f1b93165c83f0319a0bfe7e54d971b553f Author: ModelHub XC Date: Sun Jun 14 02:28:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GT-Qwen2.5-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7214b8e --- /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 +GT-Qwen2.5-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen2.5-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GT-Qwen2.5-7B.IQ4_XS.gguf b/GT-Qwen2.5-7B.IQ4_XS.gguf new file mode 100644 index 0000000..8aa3623 --- /dev/null +++ b/GT-Qwen2.5-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c751641329527ea19d9fc37651f71bc8432cef4cf3a247f5170ff92c8de6a2 +size 4250298592 diff --git a/GT-Qwen2.5-7B.Q2_K.gguf b/GT-Qwen2.5-7B.Q2_K.gguf new file mode 100644 index 0000000..89e1b88 --- /dev/null +++ b/GT-Qwen2.5-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab25201427b44eb22ea1017cf096fafe6621007a23fe7cbb21b8aea78728294 +size 3015940320 diff --git a/GT-Qwen2.5-7B.Q3_K_L.gguf b/GT-Qwen2.5-7B.Q3_K_L.gguf new file mode 100644 index 0000000..59780d8 --- /dev/null +++ b/GT-Qwen2.5-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1784af15d6c31120edc1fba8cb197fcecad1c4a9b8bde436361880c8994a9587 +size 4088459488 diff --git a/GT-Qwen2.5-7B.Q3_K_M.gguf b/GT-Qwen2.5-7B.Q3_K_M.gguf new file mode 100644 index 0000000..d5152b0 --- /dev/null +++ b/GT-Qwen2.5-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d50d81dcb12e74b0dda5b8db24d6e9463fc1838a1719a55f43ed9b3af21dfa +size 3808391392 diff --git a/GT-Qwen2.5-7B.Q3_K_S.gguf b/GT-Qwen2.5-7B.Q3_K_S.gguf new file mode 100644 index 0000000..26db36f --- /dev/null +++ b/GT-Qwen2.5-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ee2edc710aff27caba3a67d8b41814390d0dd42f0c1a9cb9a3d2267cd13471 +size 3492368608 diff --git a/GT-Qwen2.5-7B.Q4_K_M.gguf b/GT-Qwen2.5-7B.Q4_K_M.gguf new file mode 100644 index 0000000..b2d8434 --- /dev/null +++ b/GT-Qwen2.5-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb16fb2e5c2c1305f755f082deba724aa67955ba12c8328d24a85a793e3f85f +size 4683073760 diff --git a/GT-Qwen2.5-7B.Q4_K_S.gguf b/GT-Qwen2.5-7B.Q4_K_S.gguf new file mode 100644 index 0000000..04aa95c --- /dev/null +++ b/GT-Qwen2.5-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50bae035ce8df3867b66041e769292b35367b716e114f47d5e53540110d8640 +size 4457769184 diff --git a/GT-Qwen2.5-7B.Q5_K_M.gguf b/GT-Qwen2.5-7B.Q5_K_M.gguf new file mode 100644 index 0000000..f12f918 --- /dev/null +++ b/GT-Qwen2.5-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a3ab0e16bfa83ef7def63f9f5ece56585ee232d6dcdaa03a9c4f8a5013ba4c +size 5444831456 diff --git a/GT-Qwen2.5-7B.Q5_K_S.gguf b/GT-Qwen2.5-7B.Q5_K_S.gguf new file mode 100644 index 0000000..4395832 --- /dev/null +++ b/GT-Qwen2.5-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fece0552b15eb5b93e6389b9640a2f8dd2b53bd5d85211941195b9e0f98bb8d9 +size 5315176672 diff --git a/GT-Qwen2.5-7B.Q6_K.gguf b/GT-Qwen2.5-7B.Q6_K.gguf new file mode 100644 index 0000000..9a1ea94 --- /dev/null +++ b/GT-Qwen2.5-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad06a33c97115394a320b2590cec712f3ec9d1cfaa387195aebb09bc7ea783d9 +size 6254199008 diff --git a/GT-Qwen2.5-7B.Q8_0.gguf b/GT-Qwen2.5-7B.Q8_0.gguf new file mode 100644 index 0000000..d010892 --- /dev/null +++ b/GT-Qwen2.5-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2297c83fbc29800540d1d6d1c0e88ce715136aa0217a9ae0a678b5f3294823d +size 8098525408 diff --git a/GT-Qwen2.5-7B.f16.gguf b/GT-Qwen2.5-7B.f16.gguf new file mode 100644 index 0000000..80659c4 --- /dev/null +++ b/GT-Qwen2.5-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c392cea0a865e6f3a1fa10114dc66ccbc700d900cbdca2d6cbabdbbe7328c9 +size 15237853408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3afd667 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TMLR-Group-HF/GT-Qwen2.5-7B-MATH +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TMLR-Group-HF/GT-Qwen2.5-7B-MATH + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GT-Qwen2.5-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GT-Qwen2.5-7B-i1-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://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen2.5-7B-GGUF/resolve/main/GT-Qwen2.5-7B.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. + +