Downloads · 30 days
0
qwe2.5-7b-AWQ-nako13-agentbench-lora
nakotsuko13/qwe2.5-7b-AWQ-nako13-agentbench-lora
qwe2.5-7b-AWQ-nako13-agentbench-lora is a text generation model from nakotsuko13. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen2.5-7B-Instruct using LoRA + Unsloth.
Access
Public
Updated Feb 28, 2026
Parameters
7.6B
5.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.6 GB · 100%
Parameter types
How the weights are stored.
I326.5B · 86%
Try a prompt
Base models
Model card
From the Hugging Face model README
Agent SFT Model (ALFWorld & DBBench)
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen2.5-7B-Instruct using LoRA + Unsloth.
Training Objective
This adapter is trained to improve multi-turn agent task performance on:
- ALFWorld: Household interaction tasks.
- DBBench: Complex SQL database operations.
Training Configuration
- Base model: Qwen/Qwen2.5-7B-Instruct
- Max sequence length: 2048
- Epochs: 1
- Learning rate: 1e-07
- LoRA: r=64, alpha=128
Training Data
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base = "Qwen/Qwen2.5-7B-Instruct"
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.float16, device_map="auto")
model = PeftModel.from_pretrained(model, "your_id/your-repo")
- Task
- Text Generation
- Library
- peft
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Feb 28, 2026
- Updated
- Feb 28, 2026