Downloads · 30 days
9
5% of all-time downloads
logan7000/cogrpo-homo-qwen25-3b-math345-groupA
cogrpo-homo-qwen25-3b-math345-groupA is a reinforcement learning model from logan7000. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Co-GRPO (homogeneous, 2× Qwen2.5-3B cross-supervised majority-vote)
Downloads · 30 days
9
5% of all-time downloads
All-time downloads
179
Public
Parameters
242K
6.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 99%
From the Hugging Face model README
Co-GRPO (homogeneous, 2× Qwen2.5-3B cross-supervised majority-vote)
| field | value |
|---|---|
| Base model | Qwen/Qwen2.5-3B |
| Role | group A (Qwen2.5-3B) |
| Dataset | q1716523669/MATH-Level345 |
| Checkpoint | best best_model (selected by eval_reward, step 110 / 136) |
| eval_reward (pass@1, 150-prompt val) | 0.666 |
| Training status | ✅ completed |
| LR | 3e-6, cosine_with_min_lr (min 0.1×), warmup 0.03 |
| Effective batch | 128 prompts/step × 12 generations |
Fully self-contained HF model (safetensors + tokenizer + config; no optimizer state). Load directly:
from transformers import AutoModelForCausalLM, AutoTokenizer
m = "q1716523669/cogrpo-homo-qwen25-3b-math345-groupA"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, torch_dtype="bfloat16", device_map="auto")
Evaluate on MATH-500 (or the held-out 150-prompt val) with the project's standard verifier
(verifiers/qwen: math_equal / grade_answer), temperature 0.6, single-sample pass@1.
This matches how eval_reward above was computed.
Part of the co-learning (cross-supervised GRPO) study. Trained on 8×H100, ZeRO-3, vLLM colocate.