commit 9c9afa04c4f6e25d16a8334223bfa9d67a44bc40 Author: ModelHub XC Date: Sat Jul 11 05:57:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QAI-QV-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0da29f7 --- /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 +QAI-QV-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text +QAI-QV-2B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QAI-QV-2B.IQ4_XS.gguf b/QAI-QV-2B.IQ4_XS.gguf new file mode 100644 index 0000000..bcd0e2a --- /dev/null +++ b/QAI-QV-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86613f065e0539e0e0cc1cdbf4c60f9969dda3aed1ccd0aa6ce4e4b01c6867e1 +size 902182176 diff --git a/QAI-QV-2B.Q2_K.gguf b/QAI-QV-2B.Q2_K.gguf new file mode 100644 index 0000000..a72e7aa --- /dev/null +++ b/QAI-QV-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e531017b9a6c386032f14478876b8391efbbf7c6ee6a0cbadf880461c739b9f +size 676304160 diff --git a/QAI-QV-2B.Q3_K_L.gguf b/QAI-QV-2B.Q3_K_L.gguf new file mode 100644 index 0000000..67d4724 --- /dev/null +++ b/QAI-QV-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d9559ab9bad7ecef932300482ae1908d25fc6c0e4177ccf2ebc2668c5cce8a +size 880162080 diff --git a/QAI-QV-2B.Q3_K_M.gguf b/QAI-QV-2B.Q3_K_M.gguf new file mode 100644 index 0000000..5e74584 --- /dev/null +++ b/QAI-QV-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40b426ea2bd41306f3b912ab75e2d5f1a2765878075500718d6a4a5a5aba336 +size 824177952 diff --git a/QAI-QV-2B.Q3_K_S.gguf b/QAI-QV-2B.Q3_K_S.gguf new file mode 100644 index 0000000..02528ed --- /dev/null +++ b/QAI-QV-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745385657bb20ad550372ecfe572b63e4d8524a2adf640c2094789b088fd7f8d +size 760943904 diff --git a/QAI-QV-2B.Q4_K_M.gguf b/QAI-QV-2B.Q4_K_M.gguf new file mode 100644 index 0000000..41837da --- /dev/null +++ b/QAI-QV-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db5759104788a9df91b5cb18e89d07e751e6ac6062f8b44c271bec62c049c66 +size 986047776 diff --git a/QAI-QV-2B.Q4_K_S.gguf b/QAI-QV-2B.Q4_K_S.gguf new file mode 100644 index 0000000..75fb227 --- /dev/null +++ b/QAI-QV-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44dfa15bc1600912647954ee215df071fb7df0b79991aeab455cfa5ddcd1d84 +size 940311840 diff --git a/QAI-QV-2B.Q5_K_M.gguf b/QAI-QV-2B.Q5_K_M.gguf new file mode 100644 index 0000000..68baa82 --- /dev/null +++ b/QAI-QV-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9168a0a26e8412e138abd127a5efdf646c30da3d473a716282b61677df85eec +size 1125049632 diff --git a/QAI-QV-2B.Q5_K_S.gguf b/QAI-QV-2B.Q5_K_S.gguf new file mode 100644 index 0000000..274c37a --- /dev/null +++ b/QAI-QV-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060e610da4e5513df894840d3617f02af9b6ef799971580a25d2707b19e41925 +size 1098728736 diff --git a/QAI-QV-2B.Q6_K.gguf b/QAI-QV-2B.Q6_K.gguf new file mode 100644 index 0000000..6cfca29 --- /dev/null +++ b/QAI-QV-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f394bea972a46fb3cb70b207d9610b7d6e280d03f11b79bf6da5b7603d7da3c9 +size 1272739104 diff --git a/QAI-QV-2B.Q8_0.gguf b/QAI-QV-2B.Q8_0.gguf new file mode 100644 index 0000000..cc83f62 --- /dev/null +++ b/QAI-QV-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c79037585e164e0ab3f3fb8790c997512cfcabb3434d143da5033878486deed +size 1646572320 diff --git a/QAI-QV-2B.f16.gguf b/QAI-QV-2B.f16.gguf new file mode 100644 index 0000000..f9f833d --- /dev/null +++ b/QAI-QV-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6253847323c2cd5e846d6d824d99cf29d6c47f736df0e9cbcda23006d5b3267 +size 3093668640 diff --git a/QAI-QV-2B.mmproj-fp16.gguf b/QAI-QV-2B.mmproj-fp16.gguf new file mode 100644 index 0000000..ae540ad --- /dev/null +++ b/QAI-QV-2B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2388da280633726cda414216549d7dc140e4fd6a5272cbdccae54e9997834381 +size 1331656160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..31c0366 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: QualityAI/QAI-QV-2B +datasets: +- SeyedAli/Skin-Lesion-Dataset +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2_vl +--- +## About + + + + + + +static quants of https://huggingface.co/QualityAI/QAI-QV-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QAI-QV-2B-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/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-2B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QAI-QV-2B-GGUF/resolve/main/QAI-QV-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. + +