commit 8971d64b4c782dd669fbb55c616eb723db21e17d Author: ModelHub XC Date: Fri Jul 17 23:23:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-VL-7B-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..48f6d12 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2.5-VL-7B-V1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-7B-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-7B-V1.IQ4_XS.gguf b/Qwen2.5-VL-7B-V1.IQ4_XS.gguf new file mode 100644 index 0000000..7b19682 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac20c5c05e1a3c5f122d6a26d34609c31d72a21633acb2c875c64331a24921b +size 4250297792 diff --git a/Qwen2.5-VL-7B-V1.Q2_K.gguf b/Qwen2.5-VL-7B-V1.Q2_K.gguf new file mode 100644 index 0000000..d6574d9 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed810c173d1bf88d4bf63f2687d46a06e3c9e9d201e47406ecf4b74ee23a4e5 +size 3015939520 diff --git a/Qwen2.5-VL-7B-V1.Q3_K_L.gguf b/Qwen2.5-VL-7B-V1.Q3_K_L.gguf new file mode 100644 index 0000000..c084bc1 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f058c9ee4e591c2af213151b6f4b6d8c05e9ec9b17419b1c1f71ba21aec8fb8b +size 4088458688 diff --git a/Qwen2.5-VL-7B-V1.Q3_K_M.gguf b/Qwen2.5-VL-7B-V1.Q3_K_M.gguf new file mode 100644 index 0000000..753f788 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c908b410c08c867a462783964c54200409bc885611b2f770212ddf5973742ebd +size 3808390592 diff --git a/Qwen2.5-VL-7B-V1.Q3_K_S.gguf b/Qwen2.5-VL-7B-V1.Q3_K_S.gguf new file mode 100644 index 0000000..c4bddc6 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce8447fccc2c461c42939961caf93bc6803b61e0c9972bd7149dfc4d47eed8c +size 3492367808 diff --git a/Qwen2.5-VL-7B-V1.Q4_K_M.gguf b/Qwen2.5-VL-7B-V1.Q4_K_M.gguf new file mode 100644 index 0000000..78d16da --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8690535021d7b07f89436fb26188959c83c8a037399ac6b789fe401feff3cf8 +size 4683072960 diff --git a/Qwen2.5-VL-7B-V1.Q4_K_S.gguf b/Qwen2.5-VL-7B-V1.Q4_K_S.gguf new file mode 100644 index 0000000..b57d2d1 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47bf16215e9db44f967016f00b95c13ebe090f039efb7dd67d6e9c47380824a +size 4457768384 diff --git a/Qwen2.5-VL-7B-V1.Q5_K_M.gguf b/Qwen2.5-VL-7B-V1.Q5_K_M.gguf new file mode 100644 index 0000000..32cb850 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd26bfa19c1fa0151e53076a3490abbc97a22ec9870b5f5740c07173b8454c22 +size 5444830656 diff --git a/Qwen2.5-VL-7B-V1.Q5_K_S.gguf b/Qwen2.5-VL-7B-V1.Q5_K_S.gguf new file mode 100644 index 0000000..cf1ba6e --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58eade4c904fc0a07dc63e1283e573f79d08cf9aef07860464e69e6338569d24 +size 5315175872 diff --git a/Qwen2.5-VL-7B-V1.Q6_K.gguf b/Qwen2.5-VL-7B-V1.Q6_K.gguf new file mode 100644 index 0000000..e013688 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2f732e57c74c16b101768b277de94541186c7e205e4a89efea55b929caa9cc +size 6254198208 diff --git a/Qwen2.5-VL-7B-V1.Q8_0.gguf b/Qwen2.5-VL-7B-V1.Q8_0.gguf new file mode 100644 index 0000000..ef90590 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27ba5a5e1f2744abffe320fe4dfb88c60b05058a33fc892501fa6f29e528b25 +size 8098524608 diff --git a/Qwen2.5-VL-7B-V1.f16.gguf b/Qwen2.5-VL-7B-V1.f16.gguf new file mode 100644 index 0000000..54efa8c --- /dev/null +++ b/Qwen2.5-VL-7B-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f385543eea03728c017a0375f176ec297595f36f289a92f5519ef2de1447d861 +size 15237852608 diff --git a/Qwen2.5-VL-7B-V1.mmproj-Q8_0.gguf b/Qwen2.5-VL-7B-V1.mmproj-Q8_0.gguf new file mode 100644 index 0000000..87b7b71 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881e726fee6b06c802501ffcc5056038bedfcd252d31bda296dd161f8d83187b +size 856130816 diff --git a/Qwen2.5-VL-7B-V1.mmproj-f16.gguf b/Qwen2.5-VL-7B-V1.mmproj-f16.gguf new file mode 100644 index 0000000..0669af0 --- /dev/null +++ b/Qwen2.5-VL-7B-V1.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f96c718cdd813349dc1704ef4c32853cba13214705eb5592625b88da2448aab +size 1354163456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b68e68 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Zaynoid/Qwen2.5-VL-7B-V1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2_5_vl_text +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Zaynoid/Qwen2.5-VL-7B-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-7B-V1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-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/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-7B-V1-GGUF/resolve/main/Qwen2.5-VL-7B-V1.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. + +