commit 2034bb63ffef71b7664d0e49daec2c963d151a5a Author: ModelHub XC Date: Wed Jul 15 06:05:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b191e2 --- /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 +Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.f16.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.IQ4_XS.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.IQ4_XS.gguf new file mode 100644 index 0000000..40b5f19 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677601c82a8bfd7743736c5a499bd5699ce03b3f6f843c3952333117451123a1 +size 4593298496 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q2_K.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q2_K.gguf new file mode 100644 index 0000000..bd070a7 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fdafb1a0baadf64c5bff3bbaf12ddf32f6b6728bb6eb89a4aa23071046bc3f +size 3281734720 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_L.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_L.gguf new file mode 100644 index 0000000..709e982 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61355d7300148379dbbb718f9fa4cb6600bdc3a2c2689cca2b08ed7df214ab88 +size 4431395904 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_M.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_M.gguf new file mode 100644 index 0000000..3d87542 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c50643c7c8a2bd2ecce4e738165a29476550701e4ea40b805a82785edbffe6f +size 4124163136 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_S.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_S.gguf new file mode 100644 index 0000000..126c059 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4593c625456f4e1696978dad3c5c9ab1d3934c0a1045821f49939eb7cd8d47f +size 3769613376 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_M.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_M.gguf new file mode 100644 index 0000000..38fb828 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc0cf6d47f188c4ce3a7a287623b522c902863211a4942fffb67584316b6cc4 +size 5027785792 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_S.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_S.gguf new file mode 100644 index 0000000..5d02c00 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a85e6dd28c050e156e22e49c97dbd768c14a963ceb1e173e22e9534a3f0470 +size 4802014272 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_M.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_M.gguf new file mode 100644 index 0000000..921f4cf --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7728141e0e3d926e5f901f8a6b2ec465cd450d814c133159c262a8c4325546f2 +size 5851114560 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_S.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_S.gguf new file mode 100644 index 0000000..600c02a --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90145587f6b3a590fc52d69bf1f81462e9451bf23a0bcc91a67e54b7c5cb514 +size 5720763456 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q6_K.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q6_K.gguf new file mode 100644 index 0000000..e10c207 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9040bfa29410d98a0837315adc1c8b5c9eedf588daf9d8b6df94655c863e07cb +size 6725901376 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.Q8_0.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q8_0.gguf new file mode 100644 index 0000000..97828e2 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68725f7ebf484c201338f72053aea39f401de06ec88f133ad80013a39f7b3846 +size 8709520448 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.f16.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.f16.gguf new file mode 100644 index 0000000..29368dd --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409ebc32833b26439209d4a77b3d61f9218af66bbd28dd39a008cae2535f1d2c +size 16388045888 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-Q8_0.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-Q8_0.gguf new file mode 100644 index 0000000..5efc6da --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ab84e58604f472e008f139d087c3aa3f8f48c20ec74a3c8a76a41ab5c0cd87 +size 752290240 diff --git a/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-f16.gguf b/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-f16.gguf new file mode 100644 index 0000000..4646334 --- /dev/null +++ b/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0570a71e1a214edabe9177ced5a1e351c038aa6b6e15b18ad91511eb018aa128 +size 1159030336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f13caa7 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: arafid/Q3-8B-GRPO-Balanced-Vision-Freezed +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3_vl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/arafid/Q3-8B-GRPO-Balanced-Vision-Freezed + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-8B-GRPO-Balanced-Vision-Freezed-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/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-GRPO-Balanced-Vision-Freezed-GGUF/resolve/main/Q3-8B-GRPO-Balanced-Vision-Freezed.f16.gguf) | f16 | 16.5 | 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. + +