commit 3acd7b84a0ab41bf84a1cc407cc54e274fc87bc4 Author: ModelHub XC Date: Thu May 28 01:22:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/grpo-vlsp-qwen3-4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f93f9e1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +grpo-vlsp-qwen3-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +grpo-vlsp-qwen3-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b768c39 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: phamhoangf/grpo-vlsp-qwen3-4b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/phamhoangf/grpo-vlsp-qwen3-4b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#grpo-vlsp-qwen3-4b-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/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/grpo-vlsp-qwen3-4b-GGUF/resolve/main/grpo-vlsp-qwen3-4b.f16.gguf) | f16 | 8.2 | 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. + + diff --git a/grpo-vlsp-qwen3-4b.IQ4_XS.gguf b/grpo-vlsp-qwen3-4b.IQ4_XS.gguf new file mode 100644 index 0000000..993c603 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3819aab11b88f19de61bfd8d0a95c68f13bc0957f1547664d59587cfca4cc341 +size 2286316672 diff --git a/grpo-vlsp-qwen3-4b.Q2_K.gguf b/grpo-vlsp-qwen3-4b.Q2_K.gguf new file mode 100644 index 0000000..25f2a0a --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263ccfc647670ca264365d6ac57f0d560d2aa047288771268c92122474dd3bdf +size 1669500032 diff --git a/grpo-vlsp-qwen3-4b.Q3_K_L.gguf b/grpo-vlsp-qwen3-4b.Q3_K_L.gguf new file mode 100644 index 0000000..e21f2b2 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cdcbe453562a43f812cfd5cebe07b1ff0da452e79ded6009f63a1d07892ad3 +size 2239786112 diff --git a/grpo-vlsp-qwen3-4b.Q3_K_M.gguf b/grpo-vlsp-qwen3-4b.Q3_K_M.gguf new file mode 100644 index 0000000..b6191ee --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95fe32b7548537c72ac70e0206c2c35aee473989230805afac6502fc314444f +size 2075618432 diff --git a/grpo-vlsp-qwen3-4b.Q3_K_S.gguf b/grpo-vlsp-qwen3-4b.Q3_K_S.gguf new file mode 100644 index 0000000..1ab2e24 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2714f6e4709f233397e042d6283e6314bf54c2b71cba5ed3ef17c1137071419 +size 1886997632 diff --git a/grpo-vlsp-qwen3-4b.Q4_K_M.gguf b/grpo-vlsp-qwen3-4b.Q4_K_M.gguf new file mode 100644 index 0000000..3a9d2e5 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27160c2ca2756ce79883965616dfd3d79559b508851d194863cda6621fb0302d +size 2497281152 diff --git a/grpo-vlsp-qwen3-4b.Q4_K_S.gguf b/grpo-vlsp-qwen3-4b.Q4_K_S.gguf new file mode 100644 index 0000000..3829685 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc4977fdfd12d3dc9cdda7856aadebe6b1deaf91fd8651d7d4ded7d4f23fbd8 +size 2383309952 diff --git a/grpo-vlsp-qwen3-4b.Q5_K_M.gguf b/grpo-vlsp-qwen3-4b.Q5_K_M.gguf new file mode 100644 index 0000000..edfb16f --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34397eeb6bbcc7c05022b1442bb79af56e87d9d398e9d7b77033d51387cf02dc +size 2889514112 diff --git a/grpo-vlsp-qwen3-4b.Q5_K_S.gguf b/grpo-vlsp-qwen3-4b.Q5_K_S.gguf new file mode 100644 index 0000000..902d5d3 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa9f8abe15f63779a09ed1875f5d1e60f3528455a7fa1a6c1ed2d03f11bc547 +size 2823711872 diff --git a/grpo-vlsp-qwen3-4b.Q6_K.gguf b/grpo-vlsp-qwen3-4b.Q6_K.gguf new file mode 100644 index 0000000..f1226b1 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0c3b9ab2ff9ac150b2f0056d2db70f273fa2d9a4d6f7967bc714201d84c8dd +size 3306261632 diff --git a/grpo-vlsp-qwen3-4b.Q8_0.gguf b/grpo-vlsp-qwen3-4b.Q8_0.gguf new file mode 100644 index 0000000..ccf06a2 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4033cf9e6cf89ae2834ba9389ce1f6d69fc94d2aff25a6c3a469e58ae502e3b +size 4280405632 diff --git a/grpo-vlsp-qwen3-4b.f16.gguf b/grpo-vlsp-qwen3-4b.f16.gguf new file mode 100644 index 0000000..fafe4c0 --- /dev/null +++ b/grpo-vlsp-qwen3-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54219857cee8d0fea9190c17a9415a49811b9e077c10bd2a5db842e7eb050716 +size 8051285632