amr-parsing-dapo-single-single-turn-20260217-1028-global-step-1244

Model Information

• Base Model: checkpoints/amr-parsing-dapo-single/single-turn-20260217-1028/global_step_1244/actor
• Timestamp: 20260217-1028

Benchmark Results

• Benchmark File: amr-parsing-dapo-single-single-turn-20260217-1028-global-step-1244_20260217-1028.jsonl

• Score:

  • F1: 82.43
  • Precision: 83.12
  • Recall: 81.75

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("viamr-project/amr-parsing-dapo-single-single-turn-20260217-1028-global-step-1244", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("viamr-project/amr-parsing-dapo-single-single-turn-20260217-1028-global-step-1244", trust_remote_code=True)

Sample Prompt:

<|im_start|>user
Convert the following English sentence into its Abstract Meaning Representation (AMR):

<sentence>2007-08-21</sentence><|im_end|>
<|im_start|>assistant
<think>

Training Details

• Framework: veRL (Reinforcement Learning)
• Task: AMR Parsing