commit a1a294cfdda38589b33665f429db498a7279e88b Author: ModelHub XC Date: Mon Aug 17 04:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ICM-Qwen2-VL-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..87893b9 --- /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 +ICM-Qwen2-VL-2B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ICM-Qwen2-VL-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ICM-Qwen2-VL-2B.IQ4_XS.gguf b/ICM-Qwen2-VL-2B.IQ4_XS.gguf new file mode 100644 index 0000000..27fc94c --- /dev/null +++ b/ICM-Qwen2-VL-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1090a768a887ae932135d82114eaa458da8dc6ffddf5c0b0e4a6ad07e5e62790 +size 902181824 diff --git a/ICM-Qwen2-VL-2B.Q2_K.gguf b/ICM-Qwen2-VL-2B.Q2_K.gguf new file mode 100644 index 0000000..7bcc035 --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6054cf7fcd1249ff263e9c63f95bc645614b32a244e78eea2912e62ccf8ff08 +size 676303808 diff --git a/ICM-Qwen2-VL-2B.Q3_K_L.gguf b/ICM-Qwen2-VL-2B.Q3_K_L.gguf new file mode 100644 index 0000000..8b819dd --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccd9fdbc7e7532f51300f170d0b31218dbec58d04c551fca804cd0812c42cd3e +size 880161728 diff --git a/ICM-Qwen2-VL-2B.Q3_K_M.gguf b/ICM-Qwen2-VL-2B.Q3_K_M.gguf new file mode 100644 index 0000000..1f64c9f --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e9e733c684f2b0b3814f89801579fbe50b1b67526c98317b5690a34aa9a81eb +size 824177600 diff --git a/ICM-Qwen2-VL-2B.Q3_K_S.gguf b/ICM-Qwen2-VL-2B.Q3_K_S.gguf new file mode 100644 index 0000000..a72cc2e --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078b4e3858c86402a5c51e079f88bcae86a5c0f7382139b826fff9e0903a925b +size 760943552 diff --git a/ICM-Qwen2-VL-2B.Q4_K_M.gguf b/ICM-Qwen2-VL-2B.Q4_K_M.gguf new file mode 100644 index 0000000..21a748d --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04457f0e9f57f7f94ca275fc3f7ce72c357a71b22c0ce05e36b1c95f43396c48 +size 986047424 diff --git a/ICM-Qwen2-VL-2B.Q4_K_S.gguf b/ICM-Qwen2-VL-2B.Q4_K_S.gguf new file mode 100644 index 0000000..52b511d --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf9b67c868df8013d0ce2e92ac415ab8498e4a5d53de23de0764f02d3bcf4ae +size 940311488 diff --git a/ICM-Qwen2-VL-2B.Q5_K_M.gguf b/ICM-Qwen2-VL-2B.Q5_K_M.gguf new file mode 100644 index 0000000..7b787b8 --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b367f5aa4446e727caf428649b9e72cf9876de8c2e06717f59f1cfe0b514e9e +size 1125049280 diff --git a/ICM-Qwen2-VL-2B.Q5_K_S.gguf b/ICM-Qwen2-VL-2B.Q5_K_S.gguf new file mode 100644 index 0000000..cf64b44 --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e826b57725f4100498a6010715f9da0a3154fd3e6b2651bbc4ab63c112f2d380 +size 1098728384 diff --git a/ICM-Qwen2-VL-2B.Q6_K.gguf b/ICM-Qwen2-VL-2B.Q6_K.gguf new file mode 100644 index 0000000..285801b --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb7015a357313a5d376e917f390754f102146f5865b3c87ce6b10a658b94b55 +size 1272738752 diff --git a/ICM-Qwen2-VL-2B.Q8_0.gguf b/ICM-Qwen2-VL-2B.Q8_0.gguf new file mode 100644 index 0000000..b6e1609 --- /dev/null +++ b/ICM-Qwen2-VL-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa76f52cf50f58aa4b037aa579d1220792c6256ac819f1e44f179b75d1ff4856 +size 1646571968 diff --git a/ICM-Qwen2-VL-2B.f16.gguf b/ICM-Qwen2-VL-2B.f16.gguf new file mode 100644 index 0000000..c5387a0 --- /dev/null +++ b/ICM-Qwen2-VL-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a01ac5bcdb580e4f77ab4dd4ffd69a8836dc6b6f28ebf46f3fafdbef8a9e9a9 +size 3093668288 diff --git a/ICM-Qwen2-VL-2B.mmproj-fp16.gguf b/ICM-Qwen2-VL-2B.mmproj-fp16.gguf new file mode 100644 index 0000000..8891820 --- /dev/null +++ b/ICM-Qwen2-VL-2B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376346c050210fe396e971c30fdf48ad2b92ed66f1f01b0ffeb6f2dae36aad9a +size 1331656192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3426792 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: zhaoyuzhi/ICM-Qwen2-VL-2B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/zhaoyuzhi/ICM-Qwen2-VL-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ICM-Qwen2-VL-2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-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/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ICM-Qwen2-VL-2B-GGUF/resolve/main/ICM-Qwen2-VL-2B.f16.gguf) | f16 | 3.2 | 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. + +