62 lines
1.5 KiB
Markdown
62 lines
1.5 KiB
Markdown
|
---
|
||
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: apache-2.0
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- lora
|
||
|
|
- agent
|
||
|
|
- tool-use
|
||
|
|
- alfworld
|
||
|
|
- dbbench
|
||
|
|
---
|
||
|
|
|
||
|
|
# qwen25-7b-agent-exp02-C_alfv3_dbv4
|
||
|
|
|
||
|
|
This model is a fine-tuned version of **Qwen/Qwen2.5-7B-Instruct** using **LoRA + Unsloth**.
|
||
|
|
|
||
|
|
This repository contains the **full merged weights**.
|
||
|
|
No adapter loading is required.
|
||
|
|
|
||
|
|
## Training Objective
|
||
|
|
|
||
|
|
This adapter is trained to improve **multi-turn agent task performance**
|
||
|
|
on ALFWorld (household tasks) and DBBench (database operations).
|
||
|
|
|
||
|
|
Loss is applied to **all assistant turns** in the multi-turn trajectory.
|
||
|
|
|
||
|
|
## Training Configuration
|
||
|
|
|
||
|
|
- Base model: Qwen/Qwen2.5-7B-Instruct
|
||
|
|
- Data sources: ../../03_data/prepared/alfworld_v3_fixed, ../../03_data/prepared/dbbench_v4
|
||
|
|
- Method: LoRA (Unsloth)
|
||
|
|
- Max sequence length: 2048
|
||
|
|
- Epochs: 2
|
||
|
|
- Learning rate: 2e-06
|
||
|
|
- LoRA: r=64, alpha=128
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
import torch
|
||
|
|
|
||
|
|
model_id = "curio184/qwen25-7b-agent-exp02-C_alfv3_dbv4"
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
||
|
|
model_id,
|
||
|
|
torch_dtype=torch.bfloat16,
|
||
|
|
device_map="auto",
|
||
|
|
)
|
||
|
|
```
|
||
|
|
|
||
|
|
## Sources & Terms (IMPORTANT)
|
||
|
|
|
||
|
|
Training data: ../../03_data/prepared/alfworld_v3_fixed, ../../03_data/prepared/dbbench_v4
|
||
|
|
|
||
|
|
Dataset License: MIT License.
|
||
|
|
Compliance: Users must comply with the MIT license and the base model's original terms of use.
|