CoolFace
Modelpublic

SkillFactory/ablation-Qwen2.5-1.5B-Instruct-no_prompt_diversity-RL

sourceHugging Facemitupdated 10mo agoView on Hugging Face
0likes10downloads
Model Card

M-0918_origonlyprompts3args_grpo-rl

Model Details

  • —Training Method: VeRL Reinforcement Learning (RL)
  • —Stage Name: rl
  • —Experiment: 0918_origonlyprompts3args_grpo
  • —RL Framework: VeRL (Versatile Reinforcement Learning)

Training Configuration

Experiment Tracking

🔗 View complete experiment details: https://huggingface.co/datasets/TAUR-dev/D-ExpTracker_0918origonlyprompts3argsgrpo_v1

Usage

python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TAUR-dev/M-0918__orig_only_prompts_3args_grpo-rl")
model = AutoModelForCausalLM.from_pretrained("TAUR-dev/M-0918__orig_only_prompts_3args_grpo-rl")