commit 7a0ee21184d488ed2c02ae8fc8fba3a74bbfa020 Author: ModelHub XC Date: Wed Jun 17 11:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1b4b47b --- /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 +0717-GRPO-Qwen3-8B-heuristic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.f16.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0717-GRPO-Qwen3-8B-heuristic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/0717-GRPO-Qwen3-8B-heuristic.IQ4_XS.gguf b/0717-GRPO-Qwen3-8B-heuristic.IQ4_XS.gguf new file mode 100644 index 0000000..e1a9817 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba4e78e4a16ed0a435733b01e90fdd706313296271adc7b16d1fe0e2e455ad9 +size 4593296736 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q2_K.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q2_K.gguf new file mode 100644 index 0000000..7d903db --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c52dd96a9f8120c7fe6cbdfba672b17ec69929ec012ba2ad5fa83f2c44ad4f5 +size 3281732960 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q3_K_L.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_L.gguf new file mode 100644 index 0000000..205f9ad --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a7f7eaabdcb6fe4ff81f2dadfc2e883e297452b82b7b71b0b1f3e7f09883b6 +size 4431394144 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q3_K_M.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_M.gguf new file mode 100644 index 0000000..8f0d1f4 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf56f244c7642dbae0eb38f6efd09a7f46c65c97e94b6b08009e069b9652aae +size 4124161376 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q3_K_S.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_S.gguf new file mode 100644 index 0000000..4382352 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e894ce3b449c616635a54569b56dce99328d91d3c6a02e3ce78a1c332221b7 +size 3769611616 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q4_K_M.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q4_K_M.gguf new file mode 100644 index 0000000..3fac799 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d31e4d06be5fcae0a92299ceda9e506648d8e0961d0268aa5037cdf7ffc2fa +size 5027784032 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q4_K_S.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q4_K_S.gguf new file mode 100644 index 0000000..e80d042 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9138ec7e5c55b88e1dded0a162639956d8c1814805948087862d92c44191a4 +size 4802012512 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q5_K_M.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q5_K_M.gguf new file mode 100644 index 0000000..31f30e1 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc49e5e0a2a80c666f412382f9fb3c536fa19f3ca63253605dad5ff66910f98 +size 5851112800 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q5_K_S.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q5_K_S.gguf new file mode 100644 index 0000000..14085a5 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab8f26f58adef9d4c91b8f3ad72a2ee0f13f0915ff41e39aad9d965a7acd6da +size 5720761696 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q6_K.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q6_K.gguf new file mode 100644 index 0000000..e4623d4 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f11f8c801edaabd4997d7397ce65266545d9ce91cb83a5ae772cfe44b030af3 +size 6725899616 diff --git a/0717-GRPO-Qwen3-8B-heuristic.Q8_0.gguf b/0717-GRPO-Qwen3-8B-heuristic.Q8_0.gguf new file mode 100644 index 0000000..2fc63f9 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5590dae51b5d3c36c071aaa07e82bb49c41163ad4dfa6294500deb0042b245aa +size 8709518688 diff --git a/0717-GRPO-Qwen3-8B-heuristic.f16.gguf b/0717-GRPO-Qwen3-8B-heuristic.f16.gguf new file mode 100644 index 0000000..3df1c16 --- /dev/null +++ b/0717-GRPO-Qwen3-8B-heuristic.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e620903ffd95f5365cbe43045e5ebfccb78daf67be520512b0398b74bf89822e +size 16388044128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7324139 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: OptShare/0717-GRPO-Qwen3-8B-heuristic +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/OptShare/0717-GRPO-Qwen3-8B-heuristic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#0717-GRPO-Qwen3-8B-heuristic-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/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/0717-GRPO-Qwen3-8B-heuristic-GGUF/resolve/main/0717-GRPO-Qwen3-8B-heuristic.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. + +