22 lines
562 B
Markdown
22 lines
562 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: hamishivi/sft_qwen3_8b_our_sft
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- open-instruct
|
||
|
|
- grpo
|
||
|
|
- qwen3
|
||
|
|
- swerl
|
||
|
|
---
|
||
|
|
|
||
|
|
# SWERL Qwen3 8B Termigen GRPO
|
||
|
|
|
||
|
|
Final checkpoint from the `hamishivi/agent-task-termigen` GRPO run.
|
||
|
|
|
||
|
|
- Base model: `hamishivi/sft_qwen3_8b_our_sft`
|
||
|
|
- Run ID: `swerl_qwen3_8b_our_sft_agent_task_termigen_grpo__seed42`
|
||
|
|
- Run name: `swerl_qwen3_8b_our_sft_agent_task_termigen_grpo__42__1779039229`
|
||
|
|
- Training completed: 2026-05-18
|
||
|
|
|
||
|
|
This checkpoint is intended for internal evaluation and continuation experiments.
|