Ps4mas Grpo 9b Fullft Smoke Best
Run label: grpo9bfullftsmoke06240657 Checkpoint kind: best Global step: 2 Eval reward mean: -1.067 Training state: see trainingstate.json / checkpointbest.json in run dir
Fonte do modelo
- Tipo
- Text model
- Tamanho do arquivo
- Ainda não registrado
- Modelo base
- Qwen/Qwen3.5-9B
- Versão
- vRevision c9c8489
- Atualizado
- 20 de out. de 2026
- Publicador
- @yinita
- Downloads
- 16
- Parâmetros
- 9B
- Tarefas
- Legendas
- Fonte
- Hugging Face
Descrição da fonte
PS4MAS GRPO full FT — Qwen3.5-9B (best)
- Run label:
grpo_9b_fullft_smoke_0624_0657 - Checkpoint kind: best
- Global step: 2
- Eval reward mean: -1.067
- Training state: see
training_state.json/checkpoint_best.jsonin run dir
Base model: Qwen/Qwen3.5-9B
Fontes
1 fonte
Fontes
1 fonteVerificado 27 de set.
Trechos de fonte
3 trechos
Trechos de fonte
3 trechos--- base_model: Qwen/Qwen3.5-9B library_name: transformers tags: - ps4mas - grpo - full-finetune - tool-calling --- # PS4MAS GRPO full FT — Qwen3.5-9B (best) - Run label: `grpo_9b_fullft_smoke_0624_0657` - Checkpoint kind: **best** - Global step: 2 - Eval reward mean: -1.067 - Training state: see `training_state.json` / `checkpoint_best.json` in run dir Base model: [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)
Source context: 16 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yinita/ps4mas-grpo-9b-fullft-smoke-best
Source context: 38 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yinita/ps4mas-grpo-9b-fullft-smoke-best
