Downloads · 30 days
6
2% of all-time downloads
donorsim-qwen3-8b-modeAB-step75
3l3ktr4/donorsim-qwen3-8b-modeAB-step75
donorsim-qwen3-8b-modeAB-step75 is a text generation model from 3l3ktr4. Use it when you need the model to write or continue text. It is set up for transformers.
Qwen3-8B fine-tuned with GRPO (verl 0.7.1, LoRA r16/alpha32 merged into bf16 weights) on the iterated Donor's Game, Stage 2 (group games, K in {2,4,6}, within-group partner rotation with w = 1/(K-1)), mixed Mode A/B (…
All-time downloads
280
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026
- SHA
- af508190
Try a prompt
Base models
Model card
From the Hugging Face model README
donorsim-qwen3-8b-modeAB-step75
Qwen3-8B fine-tuned with GRPO (verl 0.7.1, LoRA r16/alpha32 merged into bf16 weights) on the iterated Donor's Game, Stage 2 (group games, K in {2,4,6}, within-group partner rotation with w = 1/(K-1)), mixed Mode A/B (50% of scenarios with real groupmate discussion).
True training step 75 (final step of the run). Lineage: donorsim-qwen3-8b-modeAB-step6
(steps 1-6, fixed partner) -> steps 7-11 on 4 GPUs -> steps 12-75 on 8 GPUs (run
qwen3_8b_recipT2_modeAB_from_step11_64steps_20260827_055004, global_step_64).
Merged full weights, loadable directly with transformers or vLLM (no adapter needed).
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026