commit 222e25059d69c6dfedbb7f62e4fc9581cf0201c8 Author: ModelHub XC Date: Mon Apr 13 12:09:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6dbacb5 --- /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-Thinking-2507-sft-grpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-sft-grpo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.IQ4_XS.gguf new file mode 100644 index 0000000..d18ddbe --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce9eb9540f099f77c06c0884b2708f03ce898af6fa5fea97a7ecf803c6bf9bd +size 2286316736 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q2_K.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q2_K.gguf new file mode 100644 index 0000000..6d5324b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ff8adfdb8644e14a46e17ba0e33932234ad7964c51ff725a60abcb98c932b5 +size 1669500096 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_L.gguf new file mode 100644 index 0000000..540536c --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3447e184450a24151f9ed2986400dd2ffac8311d069ae0c6c67fe52411ddfad +size 2239786176 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_M.gguf new file mode 100644 index 0000000..72ad65e --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd67146fe37c82630ea6d28ec4f8fe5605accd1ae627a02f4a3e26cb839b2cb +size 2075618496 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_S.gguf new file mode 100644 index 0000000..b355c9c --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da53f251ec6471b1b0e694cc37b704a18a624e8109a3c4e450bf0b1ff69e8c32 +size 1886997696 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_M.gguf new file mode 100644 index 0000000..5e361b2 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2806f854ffc72cee68d730d5bb98b8f2b25875abbf33fa85bda3c3fbf3c8f44 +size 2497281216 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_S.gguf new file mode 100644 index 0000000..77f974f --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fca6fc1d7faaa0df564a21d7ce5b9d5a65efb1e132ca15a2340cc3e2b34e675 +size 2383310016 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_M.gguf new file mode 100644 index 0000000..a67f930 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2924e2eefc4a4f3052da5fba5f6ee14e03866c387a1e06148511499722b0a00c +size 2889514176 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_S.gguf new file mode 100644 index 0000000..d82f516 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51b71e97aa4d92f54a2e5837ba54d2827dedf8b5f65f5bf4e25aae656ad9e1b +size 2823711936 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q6_K.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q6_K.gguf new file mode 100644 index 0000000..04dee1a --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c27057b8c12d6987bc716f0f42a1cc9d028a1dbd7a651513bf9a53c827a071 +size 3306261696 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.Q8_0.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.Q8_0.gguf new file mode 100644 index 0000000..a959e3b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d8acc106b150f3b26a028ddb6b8d8d0f30d2a68562ad16cbe5af37930b8a94 +size 4280405696 diff --git a/Qwen3-4B-Thinking-2507-sft-grpo.f16.gguf b/Qwen3-4B-Thinking-2507-sft-grpo.f16.gguf new file mode 100644 index 0000000..aca3600 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-sft-grpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa3d591844d48cd74f8657af34c470b710496f994fc6b2f8f36af8f0b1e5c2e +size 8051285696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cbf20f1 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Nofing/Qwen3-4B-Thinking-2507-sft-grpo +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/Nofing/Qwen3-4B-Thinking-2507-sft-grpo + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-sft-grpo-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-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-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-sft-grpo-GGUF/resolve/main/Qwen3-4B-Thinking-2507-sft-grpo.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. + +