viamr-project/qwen3-1.7b-amr-20260206-1038-1epoch

qwen3-1.7b-amr-20260206-1038

Model Information

• Timestamp: 20260206_121126

Benchmark Results

• Benchmark File: viamr-project_qwen3-1.7b-amr-20260206-1038.jsonl

• Score:

  • F1: 80.57
  • Precision: 81.76
  • Recall: 79.42

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("viamr-project/qwen3-1.7b-amr-20260206-1038", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("viamr-project/qwen3-1.7b-amr-20260206-1038", 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