Qwen3 4B Thinking 2507 Llmc Awq Calib Openr1 Math 220k All Train W4a16 G128 N256 S1024 | Sweet Tea StudioQwen3 4B Thinking 2507 Llmc Awq Calib Openr1 Math 220k All Train W4a16 G128 N256 S1024
Qwen3-4B-Thinking-2507-llmc-awq-calib-openr1-math-220k-all-train-w4a16-g128-n256-s1024
Verified source
Kindtext-generationBase modelQwen/Qwen3-4B-Thinking-2507Versionv78304ea2207b7ae104a3d03434a2031d3cfacab5Publisher@meteorainCgrade Model source
- Kind
- text-generation
- Base model
- Qwen/Qwen3-4B-Thinking-2507
- Version
- v78304ea2207b7ae104a3d03434a2031d3cfacab5
- Parameters
- 4B
- Tasks
- text-generation
- Source
- Hugging Face
--- library_name: transformers base_model: - Qwen/Qwen3-4B-Thinking-2507 base_model_relation: quantized pipeline_tag: text-generation tags: - Qwen3 - AWQ - W4A16 - llm-compressor --- # Qwen3-4B-Thinking-2507-llmc-awq-calib-openr1-math-220k-all-train-w4a16-g128-n256-s1024 Base model: `Qwen/Qwen3-4B-Thinking-2507` Quantized with `llm-compressor`. - method: `awq` - weight format: `W4A16` - group size: `128` - calibration dataset: `open-r1/OpenR1-Math-220k` - calibration dataset config: `all` - calibration split: `train` - calibration samples: `256` - max sequence length: `1024`
Sources & provenance
1 active source
Source evidence
3 excerpts
libraryname: transformers basemodel: Qwen/Qwen3-4B-Thinking-2507 basemodelrelation: quantized pipelinetag: text-generation tags: Qwen3 AWQ W4A16 llm-compressor
Jul 11
Qwen3-4B-Thinking-2507-llmc-awq-calib-openr1-math-220k-all-train-w4a16-g128-n256-s1024
meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-openr1-math-220k-all-train-w4a16-g128-n256-s1024
