Zum Inhalt springen
ModelÜberprüftExtern
Quelle öffnen

Ps4mas Grpo 9b Fullft Smoke Last

Run label: grpo9bfullftsmoke06240657 Checkpoint kind: last Global step: 2 Eval reward mean: n/a Training state: see trainingstate.json / checkpointbest.json in run dir

ArtText modelBasismodellQwen/Qwen3.5-9BVersionRevision 102c557Verleger@yinitaCBewertung

Modellquelle

Art
Text model
Dateigröße
Noch nicht aufgezeichnet
Basismodell
Qwen/Qwen3.5-9B
Version
vRevision 102c557
Aktualisiert
3. Okt. 2026
Verleger
@yinita
Downloads
18
Parameter
9B
Quelle
Hugging Face

Quellenbeschreibung

PS4MAS GRPO full FT — Qwen3.5-9B (last)

  • Run label: grpo_9b_fullft_smoke_0624_0657
  • Checkpoint kind: last
  • Global step: 2
  • Eval reward mean: n/a
  • Training state: see training_state.json / checkpoint_best.json in run dir

Base model: Qwen/Qwen3.5-9B

Quellen

1 Quelle
Hugging FacePrimärVersion 102c557a803234547fedc9f15ff78017c35e62f0
huggingface.co/yinita/ps4mas-grpo-9b-fullft-smoke-last/tree/102c557a803234547fedc9f15ff78017c35e62f0

Verifiziert 3. Okt.

Quellenauszüge

3 Auszüge

--- base_model: Qwen/Qwen3.5-9B library_name: transformers tags: - ps4mas - grpo - full-finetune - tool-calling --- # PS4MAS GRPO full FT — Qwen3.5-9B (last) - Run label: `grpo_9b_fullft_smoke_0624_0657` - Checkpoint kind: **last** - Global step: 2 - Eval reward mean: n/a - 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: 18 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yinita/ps4mas-grpo-9b-fullft-smoke-last

Source context: 38 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yinita/ps4mas-grpo-9b-fullft-smoke-last