commit 4e2d827604c2c139826a0b395d1d6635ba30cdca Author: ModelHub XC Date: Mon Jun 1 10:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AWARES-Qwen2.5-VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b8b3abb --- /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 +AWARES-Qwen2.5-VL-7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AWARES-Qwen2.5-VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AWARES-Qwen2.5-VL-7B.IQ4_XS.gguf b/AWARES-Qwen2.5-VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..b41beae --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28326b0d38962d97e143fe2b00c564f3a49063c52f5109de993ddcfa676a0dc0 +size 4250297856 diff --git a/AWARES-Qwen2.5-VL-7B.Q2_K.gguf b/AWARES-Qwen2.5-VL-7B.Q2_K.gguf new file mode 100644 index 0000000..3305ec0 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be989bbfa68c41d4bffe02203715ca0199c76fe18e19e3c0c50835022b13eb60 +size 3015939584 diff --git a/AWARES-Qwen2.5-VL-7B.Q3_K_L.gguf b/AWARES-Qwen2.5-VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..1da5c41 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615239d8014c456e90b694eeb901be7adb1bfecbc3291f97aff64cfb4adb4cfc +size 4088458752 diff --git a/AWARES-Qwen2.5-VL-7B.Q3_K_M.gguf b/AWARES-Qwen2.5-VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..c5204b5 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0dc7ac7bf6dee40b41cbea2e00501ec03e8d947b4fd9463fb2cc370d7dfae19 +size 3808390656 diff --git a/AWARES-Qwen2.5-VL-7B.Q3_K_S.gguf b/AWARES-Qwen2.5-VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..6500423 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1da21a71a3d5770b8588e495e02233a450427af32fccdc67e84259fb21739d +size 3492367872 diff --git a/AWARES-Qwen2.5-VL-7B.Q4_K_M.gguf b/AWARES-Qwen2.5-VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..e33c37b --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2245729cdf9114da89a43d80a03bf59beeb3fd8211682f07d4b466742a7351d +size 4683073024 diff --git a/AWARES-Qwen2.5-VL-7B.Q4_K_S.gguf b/AWARES-Qwen2.5-VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..2f4470d --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3646495722980f5dac2e3b2e82cdcebdad3f206fa6cdba14c9c1eea183bcc5c +size 4457768448 diff --git a/AWARES-Qwen2.5-VL-7B.Q5_K_M.gguf b/AWARES-Qwen2.5-VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..c8a84dd --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e66c627f2ea3e6700e9688ab4c1eaff6e979c6b8f4a521705e3d03080f7dc692 +size 5444830720 diff --git a/AWARES-Qwen2.5-VL-7B.Q5_K_S.gguf b/AWARES-Qwen2.5-VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..11f778a --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d711fb22e87b6cffd277af419557c4be7d996ed22a5f95a727eed9f615e8d66 +size 5315175936 diff --git a/AWARES-Qwen2.5-VL-7B.Q6_K.gguf b/AWARES-Qwen2.5-VL-7B.Q6_K.gguf new file mode 100644 index 0000000..0a2b8e1 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a06b634b42f1fad4bcff4103267bfcc6b67dc55a74223151f1bb826b06d930 +size 6254198272 diff --git a/AWARES-Qwen2.5-VL-7B.Q8_0.gguf b/AWARES-Qwen2.5-VL-7B.Q8_0.gguf new file mode 100644 index 0000000..e319573 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c49ac4fc1d9a4c4e373d4d0c8a24e1b1fb0b5d56528a1dd9a584d3e6d546e9 +size 8098524672 diff --git a/AWARES-Qwen2.5-VL-7B.f16.gguf b/AWARES-Qwen2.5-VL-7B.f16.gguf new file mode 100644 index 0000000..5f665e8 --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59e0f476f172ab09432a6ddccd7942c9a2d7a285d4f29d25ead705bf964bfdb +size 15237852672 diff --git a/AWARES-Qwen2.5-VL-7B.mmproj-Q8_0.gguf b/AWARES-Qwen2.5-VL-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..cfce80c --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e9171c30056288c54bf9fef8b61b8a47c5f9f62bfadf8fe799c86aee5803dc +size 856130848 diff --git a/AWARES-Qwen2.5-VL-7B.mmproj-f16.gguf b/AWARES-Qwen2.5-VL-7B.mmproj-f16.gguf new file mode 100644 index 0000000..e912b1b --- /dev/null +++ b/AWARES-Qwen2.5-VL-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c447c67f95f7ad60471a058f65a091114f199b8719bb338a06a60a7a1bf8c5 +size 1354163488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d4d5fad --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Kimhi/AWARES-Qwen2.5-VL-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vision-language-model +- qwen2.5-vl +- adaptive-resolution +- GRPO +- multi-turn +- tool-use +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Kimhi/AWARES-Qwen2.5-VL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AWARES-Qwen2.5-VL-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-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/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-Qwen2.5-VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AWARES-Qwen2.5-VL-7B-GGUF/resolve/main/AWARES-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. + +