38 lines
1003 B
Markdown
38 lines
1003 B
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- ja
|
||
|
|
- en
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
||
|
|
tags:
|
||
|
|
- text-generation
|
||
|
|
- agent
|
||
|
|
- sql
|
||
|
|
- alfworld
|
||
|
|
- dbagent
|
||
|
|
---
|
||
|
|
|
||
|
|
# matsuo-llm-advanced-phase-e2a
|
||
|
|
|
||
|
|
Fine-tuned from Qwen/Qwen2.5-7B-Instruct for agent tasks (DBBench + ALFWorld).
|
||
|
|
|
||
|
|
## Datasets
|
||
|
|
|
||
|
|
- `u-10bei/dbbench_sft_dataset_react_v4` — Listed in the organizer-shared dataset list.
|
||
|
|
Used as provided (no modification). Third-party synthetic SFT for DBBench format alignment;
|
||
|
|
all tables, data, and queries are independently generated
|
||
|
|
(per dataset description: "to avoid test data leakage").
|
||
|
|
- `xlangai/spider` — CC BY-SA 4.0 (Yale/Columbia Spider project)
|
||
|
|
- `birdsql/bird_mini_dev` — CC BY-SA 4.0 (HKU)
|
||
|
|
- Official ALFWorld v5 dataset — Organizer-provided, used as provided.
|
||
|
|
|
||
|
|
## Compliance
|
||
|
|
|
||
|
|
- Evaluation data not used in training: No analysis of evaluation test data was conducted.
|
||
|
|
- LLM was not used for data quality filtering or selection.
|
||
|
|
- Inference code not modified.
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
Compatible with vLLM v0.13.0+.
|