test_global_step_10_ragen

This model was exported from a UFO training checkpoint.

  • Base model: Qwen/Qwen2.5-3B-Instruct
  • Source checkpoint: /workspace/ufb/outputs/checkpoints/exp1_MetamathQA/top_k/global_step_10/actor
  • Exported step: global_step_10

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "/workspace/ufb/outputs/hf/test_global_step_10_ragen"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
Downloads last month
13
Safetensors
Model size
3B params
Tensor type
BF16
·
Video Preview
loading

Model tree for ZihanWang314/test_global_step_10_ragen

Base model

Qwen/Qwen2.5-3B
Finetuned
(1176)
this model