commit 03bb114ccd77c22f632142080736c31a038c776a Author: ModelHub XC Date: Thu Jul 23 10:10:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..242bf4e --- /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 +Qwen3-4B-tau2-grpo-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-tau2-grpo-v0.1.IQ4_XS.gguf b/Qwen3-4B-tau2-grpo-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..27d3297 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1554a508f1501b94cd2993e5681a502aca94c39e27ab56d4cfc19f75d5ce20ec +size 2286315104 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q2_K.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q2_K.gguf new file mode 100644 index 0000000..2806b35 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea62be1c799e340e98512f8a9f82658dd8eef7f2998b9cdde0e8e1bcf75a9fd8 +size 1669498464 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q3_K_L.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..98b9609 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d59d55e30371b557189c1bc9ec6f6468f4369b6736b03d5c13db265bd00becf +size 2239784544 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q3_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..11d18f2 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b790811db3c3c9356f49e65a44c98f3cb1c0d4c30ccacb88addfffc7726142e +size 2075616864 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q3_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..c5aeac2 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace35944ab1ad93b245370350425de608aa492d70e0b69ff73540b4fcf0710bc +size 1886996064 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q4_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..08a5db8 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d69da942b399da698aa138d9af4e69d0b91547650d4ad3bc4db2bf92f1b41fc +size 2497279584 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q4_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..bdd4faf --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2e447512a6d5c53e4286054a50b3c3d43feb27f8f26c4ee9a1b6e9e913f2dd +size 2383308384 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q5_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..0c9d29c --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d269c93b6af605bc69e6ddc670b6f5034eae80bd97b699b07cb16aeb61b278ee +size 2889512544 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q5_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..2d10ed7 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ccb3e5a472d8ddf2225b562c791dbae8a2cc5008b1aca64ea35f68602c8ac54 +size 2823710304 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q6_K.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q6_K.gguf new file mode 100644 index 0000000..48f0958 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf2609c1c57af617e8ac64a17e8dc78916e652dde72c04c10dd4540c39d8d78 +size 3306260064 diff --git a/Qwen3-4B-tau2-grpo-v0.1.Q8_0.gguf b/Qwen3-4B-tau2-grpo-v0.1.Q8_0.gguf new file mode 100644 index 0000000..a66c5d1 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fb2a2fd773980fbcf899487e74160c5f805975c17cb28672e7702de0733140 +size 4280404064 diff --git a/Qwen3-4B-tau2-grpo-v0.1.f16.gguf b/Qwen3-4B-tau2-grpo-v0.1.f16.gguf new file mode 100644 index 0000000..e9c9ed5 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd273914ead536bc5271701efc75e2152421a86a76925a58eb060b0727a163a +size 8051284064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..74d9420 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: zjxia/Qwen3-4B-tau2-grpo-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zjxia/Qwen3-4B-tau2-grpo-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-tau2-grpo-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF +## 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/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.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. + +