qwen3-0.6b-amr-20260205-0900

Model Information

• Timestamp: 20260205_101748

Benchmark Results

• Benchmark File: viamr-project_qwen3-0.6b-amr-20260205-0900.jsonl

• Score:

  • F1: 79.69
  • Precision: 80.17
  • Recall: 79.22

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("viamr-project/qwen3-0.6b-amr-20260205-0900", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("viamr-project/qwen3-0.6b-amr-20260205-0900", trust_remote_code=True)

Sample Prompt:

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

<sentence>He needs to conduct a beer summit between Palin and NBC.</sentence><|im_end|>
<|im_start|>assistant
<think>

</think>

Training Details

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