M-0909__0epoch_3args_grpo-rl

Model Details

Training Method: VeRL Reinforcement Learning (RL)
Stage Name: rl
Experiment: 0909__0epoch_3args_grpo
RL Framework: VeRL (Versatile Reinforcement Learning)

Training Configuration

Experiment Tracking

🔗 View complete experiment details: https://huggingface.co/datasets/TAUR-dev/D-ExpTracker__0909__0epoch_3args_grpo__v1

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TAUR-dev/M-0909__0epoch_3args_grpo-rl")
model = AutoModelForCausalLM.from_pretrained("TAUR-dev/M-0909__0epoch_3args_grpo-rl")

Downloads last month: 44

Safetensors

Model size

2B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including SkillFactory/ablation-Qwen2.5-1.5B-Instruct-instruction_prompt-RL

Ablation Models

Collection

All of these models were trained on countdown 3args with Qwen2.5-1.5B-Instruct • 7 items • Updated 8 days ago