amr-parsing-dapo-single-single-turn-20260216-0038-global-step-311

Model Information

• Base Model: checkpoints/amr-parsing-dapo-single/single-turn-20260216-0038/global_step_311/actor
• Timestamp: 20260216-0038

Benchmark Results

• Benchmark File: amr-parsing-dapo-single-single-turn-20260216-0038-global-step-311_20260216-0038.jsonl

• Score:

  • F1: 82.16
  • Precision: 83.07
  • Recall: 81.28

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("viamr-project/amr-parsing-dapo-single-single-turn-20260216-0038-global-step-311", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("viamr-project/amr-parsing-dapo-single-single-turn-20260216-0038-global-step-311", 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