Downloads · 30 days
12
16% of all-time downloads
yoda-rlaif-runC
n-deshpande/yoda-rlaif-runC
yoda-rlaif-runC is a machine learning model from n-deshpande. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
GRPO (TRL 1.13, vLLM colocate) LoRA adapter (r=32) trained on top of n-deshpande/yoda-run3-sft/merged for 300 steps (16 prompts x 8 completions, T=1.0, lr 1e-5 constant, KL beta 0.04 to the merged weights). Run C: A's…
All-time downloads
76
Public
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 95%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- bbb1684c
Base models
Model card
From the Hugging Face model README
yoda-rlaif-runC
GRPO (TRL 1.13, vLLM colocate) LoRA adapter (r=32) trained on top of n-deshpande/yoda-run3-sft/merged for 300 steps
(16 prompts x 8 completions, T=1.0, lr 1e-5 constant, KL beta 0.04 to the merged weights). Run C: A's prompts plus +3 x verifier(correct) on math prompts (Checkpoint-3 preview).
Reward: persona judge (DeepSeek V4 Flash, 0-10 rubric, one call per group of 8, k=3) minus rule penalties for tics, length and missing boxed answer.
final/: the step-300 adapter. checkpoint-N/: adapters every 25 steps. Load with PEFT on the merged SFT weights, or with vLLM enable_lora.
Results, statistics and the full log of what was done: https://github.com/harvard-cs2881f26/hw1-wu-ge-deshpande (checkpoint_2). Reward logs: n-deshpande/yoda-rlaif-logs.
- Library
- peft
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026