commit e56f364df44b094530f989aef4dc1db7f693cc29 Author: ModelHub XC Date: Sun Jul 12 09:54:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..639a6d9 --- /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 +PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PMLLM-Qwen3-VL-8B-DrGRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.IQ4_XS.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.IQ4_XS.gguf new file mode 100644 index 0000000..584686f --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7074bb42b0e955ec3dc76d8dd2c8101b9e48cf38d9aa7f7a6816c46decedb55e +size 4593297984 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q2_K.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q2_K.gguf new file mode 100644 index 0000000..e6a8546 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750173db31fbdff219e0e5df95d5ed55da69f7c0029bf68ec8a1fc360e5c5cfc +size 3281734208 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_L.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_L.gguf new file mode 100644 index 0000000..cdc1b11 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1652f5c88527b9c9d3e157f187dd6816e676ab74837b1a7b9440bd576bf3091 +size 4431395392 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_M.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_M.gguf new file mode 100644 index 0000000..92ec5e5 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bbae72936abd822dc83a8917a0bb50bec16f1d3ca5d0751c5e80f899acfb6f +size 4124162624 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_S.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_S.gguf new file mode 100644 index 0000000..f502ed5 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce81a0595bcfab74d931df586494bba1bdc36623930bf3ed96e28584f0a88ac +size 3769612864 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_M.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_M.gguf new file mode 100644 index 0000000..1777a62 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39966a162072c342ce5ed37ca75a1e452d59667cbb10eaccc8d486c02043855 +size 5027785280 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_S.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_S.gguf new file mode 100644 index 0000000..b154a7d --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5214dab804e30b3d71f93d28dee39d961225892b4c2a66caaefba5d20d472d1 +size 4802013760 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_M.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_M.gguf new file mode 100644 index 0000000..f84c49c --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbc276763740ad3732da669a12ef7eedb7d859fa6c1e8f2068a63cfc864b87c +size 5851114048 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_S.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_S.gguf new file mode 100644 index 0000000..a323231 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7a5915db0a95ffd75aa2ec57fb339d1d8257f2d4279559fb12c9cac3324238 +size 5720762944 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q6_K.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q6_K.gguf new file mode 100644 index 0000000..158c0e4 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b6546710c053874e4a15692e59bbb25a41c6d69e5d46380eb36c87082add75 +size 6725900864 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.Q8_0.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.Q8_0.gguf new file mode 100644 index 0000000..bbe7634 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd4fa1bb30da3207fac9f33418929d2d3817e18c6a05895d1c776f96045c4d7 +size 8709519936 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.f16.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.f16.gguf new file mode 100644 index 0000000..d5ed597 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b70b08f5d2d7a2d4c24e80089645d70343cf819dae2ce57162cbd5e18a553fd +size 16388045376 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-Q8_0.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-Q8_0.gguf new file mode 100644 index 0000000..49db546 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d835daeaf89a79d5317b1a1e57b773691ddd278f4234297fff1fa90544dbec5d +size 752289728 diff --git a/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-f16.gguf b/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-f16.gguf new file mode 100644 index 0000000..6e2ee29 --- /dev/null +++ b/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb5a0ac825521e9187aef4a0ea73c65f7d730bea9aefb6f8f626293f9ebd8f0 +size 1159029824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e29253f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Yeongtak/PMLLM-Qwen3-VL-8B-DrGRPO +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yeongtak/PMLLM-Qwen3-VL-8B-DrGRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PMLLM-Qwen3-VL-8B-DrGRPO-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/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PMLLM-Qwen3-VL-8B-DrGRPO-GGUF/resolve/main/PMLLM-Qwen3-VL-8B-DrGRPO.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. + +