Instructions to use peanuts33/advanced-test04 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use peanuts33/advanced-test04 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from peanuts33/advanced-test04: direct link, hf CLI and curl.
- Browser
- Download file 1.25 kB
-
https://huggingface.co/peanuts33/advanced-test04/resolve/main/README.md
- Command line
-
hf download hf://peanuts33/advanced-test04/README.md
-
curl -L -o README.md https://huggingface.co/peanuts33/advanced-test04/resolve/main/README.md
1.25 kB
| base_model: Qwen/Qwen3-4B-Instruct-2507 | |
| datasets: | |
| - u-10bei/sft_alfworld_trajectory_dataset_v3 | |
| - u-10bei/sft_alfworld_trajectory_dataset_v5 | |
| - u-10bei/dbbench_sft_dataset_react_v4 | |
| language: | |
| - en | |
| license: apache-2.0 | |
| library_name: peft | |
| pipeline_tag: text-generation | |
| tags: | |
| - lora | |
| - agent | |
| - alfworld | |
| - dbbench | |
| # qwen3-4b-agent-trajectory-lora-test04 | |
| LoRA adapter fine-tuned from **Qwen/Qwen3-4B-Instruct-2507** using Unsloth. | |
| ## Key Improvement (vs test03) | |
| ALFWorld training data (v3/v5) was in function-calling format, but the evaluation | |
| environment expects ReAct text format (THOUGHT/ACTION). This mismatch caused test03 | |
| to score significantly lower than test02. | |
| test04 converts ALFWorld data to ReAct format before training: | |
| - `assistant` + `tool_calls` → `THOUGHT: <think>\nACTION: <action>` text | |
| - `tool` role → `user` role (matching eval environment observation format) | |
| ## Training Configuration | |
| - Base model: Qwen/Qwen3-4B-Instruct-2507 | |
| - Data: ALFWorld (v3+v5, ReAct-converted) + DBBench v4 × 3 | |
| - Max sequence length: 2048 | |
| - Epochs: 2 | |
| - Learning rate: 2e-06 | |
| - LoRA: r=64, alpha=128 | |
| ## Sources | |
| - u-10bei/sft_alfworld_trajectory_dataset_v3 | |
| - u-10bei/sft_alfworld_trajectory_dataset_v5 | |
| - u-10bei/dbbench_sft_dataset_react_v4 | |