Opera / README.md
beyoru's picture
Update README.md
7b6bceb verified
|
Raw
History Blame Contribute Delete
771 Bytes
---
license: apache-2.0
base_model: Qwen/Qwen3.6-27B
tags:
- function-calling
- tool-use
- agent
- grpo
- intuitor
- self-certainty
- qwen3_5
pipeline_tag: text-generation
library_name: transformers
---
# Opera
RL fine-tune of **Qwen3.6-27B** for agentic tool-calling, trained with GRPO + LoRA
and a composite reward: rule-based (function name + argument-subset partial credit),
structural tool-call validity, and **Intuitor self-certainty** (arXiv:2505.19590),
rule and self-certainty weighted 1.0 each (normalized separately, then combined).
## Serve (vLLM >= 0.25, no --trust-remote-code)
```bash
vllm serve beyoru/Opera --served-model-name opera -tp 4 --max-model-len 16384 \
--enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3
```