ModelVerifiedExternal

Ps4mas Grpo 9b Fullft Smoke Best

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

Verified source

Sourcehuggingface.co/yinita/ps4mas-grpo-9b-fullft-smoke-best

Kindimage-text-to-textBase modelQwen/Qwen3.5-9BVersionvc9c84899c13c505d17944c87bc4e0116c1665c84Publisher@yinitaCgrade

Model source

Kind: image-text-to-text
Base model: Qwen/Qwen3.5-9B
Version: vc9c84899c13c505d17944c87bc4e0116c1665c84
Publisher: @yinita
Parameters: 9B
Source: Hugging Face

Source description

--- 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)

Sources & provenance

1 active source

Hugging FaceRepresentative

huggingface.co/yinita/ps4mas-grpo-9b-fullft-smoke-best

highest_eligible_score

Verified Jul 11

Source evidence

3 excerpts

Readme excerptJul 11huggingface.co/yinita/ps4mas-grpo-9b-fullft-smoke-best

basemodel: Qwen/Qwen3.5-9B libraryname: transformers tags: ps4mas grpo full-finetune tool-calling

SummaryJul 11