commit b8f63b508bbb9b99948fe690859e81fb64b7d289 Author: ModelHub XC Date: Thu Jun 4 18:06:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f35e40e --- /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 +ArrowRL-Qwen2.5-VL-7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArrowRL-Qwen2.5-VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArrowRL-Qwen2.5-VL-7B.IQ4_XS.gguf b/ArrowRL-Qwen2.5-VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..c2f3b3b --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56204a6b709d80b112134ae2227a6583365c39233254ef8f4c688bbe546edab4 +size 4250297728 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q2_K.gguf b/ArrowRL-Qwen2.5-VL-7B.Q2_K.gguf new file mode 100644 index 0000000..ed63536 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc162043a4be3787087a426563bdcb8188c168bb5d7fe5e0354fed616e3b494 +size 3015939456 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q3_K_L.gguf b/ArrowRL-Qwen2.5-VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..b76cc7e --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9369d3bad8c7a304b763037c7505e4e10c90a355eeef88b1059d299ca9206b4c +size 4088458624 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q3_K_M.gguf b/ArrowRL-Qwen2.5-VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..a58a619 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604b2ba46b2ebc6cb1e68b0ea5db7ea35a8ac1178a4bdc57d6607c5c4686dcb9 +size 3808390528 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q3_K_S.gguf b/ArrowRL-Qwen2.5-VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4a70919 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f57b8f40d15322de7ff6996ed98525146b5f4b2d2d32e6790cf9361c0027ff9 +size 3492367744 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q4_K_M.gguf b/ArrowRL-Qwen2.5-VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..e7f5d1f --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357cdedc7bc1d9e428e8a488810f2f859044dc3e23d127675dbf238c4c98db1b +size 4683072896 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q4_K_S.gguf b/ArrowRL-Qwen2.5-VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..536d219 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1385f230f4be4f29e5355358c674374adc022b8f65ce18eece7eed0ff284715 +size 4457768320 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q5_K_M.gguf b/ArrowRL-Qwen2.5-VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..f909a8c --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175421971418edcf088039dec4206554f52ba0b9b894a9c011f5713cceea0de9 +size 5444830592 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q5_K_S.gguf b/ArrowRL-Qwen2.5-VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..10be62a --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9e8c4caab188978a35bffbb96ad0c066601ea1f7a007d00fa919017c8ead81 +size 5315175808 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q6_K.gguf b/ArrowRL-Qwen2.5-VL-7B.Q6_K.gguf new file mode 100644 index 0000000..9405c75 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d5a7ab8e0d7bc52a4dfa981848168b9522efbdd5dbf6c60a0a039657ed27c0 +size 6254198144 diff --git a/ArrowRL-Qwen2.5-VL-7B.Q8_0.gguf b/ArrowRL-Qwen2.5-VL-7B.Q8_0.gguf new file mode 100644 index 0000000..36b22b2 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4d3adaa6afbcc2c17091a43e342d02f2e6dddf9b1db901e95f71c3490d5744 +size 8098524544 diff --git a/ArrowRL-Qwen2.5-VL-7B.f16.gguf b/ArrowRL-Qwen2.5-VL-7B.f16.gguf new file mode 100644 index 0000000..62d11be --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5fc168072a1e2efe4ca883920acd060ef47a2d9e73d28f803338b38b526bf3 +size 15237852544 diff --git a/ArrowRL-Qwen2.5-VL-7B.mmproj-Q8_0.gguf b/ArrowRL-Qwen2.5-VL-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..1292107 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056e37dced1f6445828332e5611e9cb379dca903eaf6001a2f3ec029ef93460d +size 853120096 diff --git a/ArrowRL-Qwen2.5-VL-7B.mmproj-f16.gguf b/ArrowRL-Qwen2.5-VL-7B.mmproj-f16.gguf new file mode 100644 index 0000000..9b80df1 --- /dev/null +++ b/ArrowRL-Qwen2.5-VL-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e54e3915ca3ffc4e8d8fbae09164446b1aa9cc9354eee4d68751db9ba2ca18c +size 1354163296 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fdafc8c --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: sherryxzh/ArrowRL-Qwen2.5-VL-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sherryxzh/ArrowRL-Qwen2.5-VL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ArrowRL-Qwen2.5-VL-7B-GGUF).*** + +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/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArrowRL-Qwen2.5-VL-7B-GGUF/resolve/main/ArrowRL-Qwen2.5-VL-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. + +