Ir para o conteúdo
ModelVerificadoExterno
Baixar

Qwen3 4B Thinking 2507 Llmc Awq Calib Codeforces Cots Solutions Train W4a16 G128 N256 S1024

method: awq weight format: W4A16 group size: 128 calibration dataset: open-r1/codeforces-cots calibration dataset config: solutions calibration split: train calibration samples: 256 max sequence length: 1024

Fontehuggingface.co/meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024/tree/f36fa0d906667298d8d376af5faddde0d387dad0
TipoText modelModelo baseQwen/Qwen3-4B-Thinking-2507VersãomodelPublicador@meteorainCnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
2,48 GB
Modelo base
Qwen/Qwen3-4B-Thinking-2507
Versão
vmodel
Atualizado
4 de out. de 2026
Publicador
@meteorain
Downloads
3
Parâmetros
4B
Tarefas
Geração de texto
Fonte
Hugging Face

Descrição da fonte

Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-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/codeforces-cots
  • calibration dataset config: solutions
  • calibration split: train
  • calibration samples: 256
  • max sequence length: 1024

Fontes

1 fonte
Hugging FacePrimárioVersão f36fa0d906667298d8d376af5faddde0d387dad0
huggingface.co/meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024/tree/f36fa0d906667298d8d376af5faddde0d387dad0

Verificado 4 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 2,48 GB · SHA-256 84f2c1e900fb…db2b · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024

--- 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-codeforces-cots-solutions-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/codeforces-cots` - calibration dataset config: `solutions` - calibration split: `train` - calibration samples: `256` - max sequence length: `1024`

Note4 de out.huggingface.co/meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024

Source context: 3 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024

Note18 de jul.huggingface.co/meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024

Source context: 46 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo meteorain/Qwen3-4B-Thinking-2507-llmc-awq-calib-codeforces-cots-solutions-train-w4a16-g128-n256-s1024