commit 065ad5cd151142afb8fd972bf0aea7589d49c1f1 Author: ModelHub XC Date: Mon Jul 20 01:53:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5VL-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6fb5bce --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Qwen2.5VL-7B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5VL-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5VL-7B-Instruct.IQ4_XS.gguf b/Qwen2.5VL-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..51759b3 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaba55904d8dc4d153a3176c1306cddd6f41172465f0a54e23234c00358c040 +size 4250297408 diff --git a/Qwen2.5VL-7B-Instruct.Q2_K.gguf b/Qwen2.5VL-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..8291df6 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97b06204421f15e0ab241dd10ee333fd880b58e9a8da28f34f98e682d42ced19 +size 3015939136 diff --git a/Qwen2.5VL-7B-Instruct.Q3_K_L.gguf b/Qwen2.5VL-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..75cda14 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d41993a2d3d028a28013b1a9c2a49a0182d061fcd33f5987861329caa74cb45 +size 4088458304 diff --git a/Qwen2.5VL-7B-Instruct.Q3_K_M.gguf b/Qwen2.5VL-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d756ed2 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9095d80f02ba7559ef558819a5009cc9215c27cac739f4daaf2654a82866db +size 3808390208 diff --git a/Qwen2.5VL-7B-Instruct.Q3_K_S.gguf b/Qwen2.5VL-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..10e1328 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cf26dd0e983249977cc553cd08a112de97a68ac88813bb2fcc872b33554f65 +size 3492367424 diff --git a/Qwen2.5VL-7B-Instruct.Q4_K_M.gguf b/Qwen2.5VL-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..be07520 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5d3931b2dd547417f57eb174a254342901e777754bab5b04ec9e1e096288ef +size 4683072576 diff --git a/Qwen2.5VL-7B-Instruct.Q4_K_S.gguf b/Qwen2.5VL-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e5e84c4 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8df522bb8c465bcd5be96b1e4206c91dac3e1472a2871581895c332d552d1b1 +size 4457768000 diff --git a/Qwen2.5VL-7B-Instruct.Q5_K_M.gguf b/Qwen2.5VL-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..fb4ee02 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c66ae689d413a494fd5056092090deb94fb3ef11fc1fc4d8e0b5d8bbcd48f80 +size 5444830272 diff --git a/Qwen2.5VL-7B-Instruct.Q5_K_S.gguf b/Qwen2.5VL-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1372012 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe122d1548021bbc252e6c71f01e3ff847cbfee80a8c3a7e1a8cbb52d266bf32 +size 5315175488 diff --git a/Qwen2.5VL-7B-Instruct.Q6_K.gguf b/Qwen2.5VL-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ac2eb42 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e63126b0a302f984b64eeeb059f77f6dbe607020e3a9ef6ebc6fb009bcf1714 +size 6254197824 diff --git a/Qwen2.5VL-7B-Instruct.Q8_0.gguf b/Qwen2.5VL-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..cb41d94 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb39746eb70a329208512e40a28fdc0b60a01abb28103f3d4c195fadf3d0eec +size 8098524224 diff --git a/Qwen2.5VL-7B-Instruct.f16.gguf b/Qwen2.5VL-7B-Instruct.f16.gguf new file mode 100644 index 0000000..2090804 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bceb60bb12f22ea172fa0adf1a913ae2a70c6187e0f0a205d935397bafb32ee1 +size 15237852224 diff --git a/Qwen2.5VL-7B-Instruct.mmproj-Q8_0.gguf b/Qwen2.5VL-7B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..d8d8bc3 --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f5f81b06740f07351736c6e70cccc23115eceba0f116117d1000d68e812ce2 +size 856130336 diff --git a/Qwen2.5VL-7B-Instruct.mmproj-f16.gguf b/Qwen2.5VL-7B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..8a6197d --- /dev/null +++ b/Qwen2.5VL-7B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2738be5d2e95659320e024003d0c0e2081fa88810f1f392fccc443353032c51 +size 1354162976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..137119c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: gaoqie/Qwen2.5VL-7B-Instruct-fire +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/gaoqie/Qwen2.5VL-7B-Instruct-fire + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5VL-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-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/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5VL-7B-Instruct-GGUF/resolve/main/Qwen2.5VL-7B-Instruct.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. + +