Downloads · 30 days
6
14% of all-time downloads
TrajAD-Qwen3-8B-Adapter
GuQ1ng/TrajAD-Qwen3-8B-Adapter
TrajAD-Qwen3-8B-Adapter is a text generation model from GuQ1ng. Use it when you need the model to write or continue text. It is set up for peft.
这是一个基于 Qwen/Qwen3-8B 微调得到的 QLoRA adapter。
All-time downloads
42
Public
Repo size
186 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors175 MB · 92%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026
- SHA
- 70faeb8e
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-8B-MyAdapter
这是一个基于 Qwen/Qwen3-8B 微调得到的 QLoRA adapter。
Notes
- 仅包含 adapter 权重，不包含 base model
- 用途：Trajectory Anomaly Detection for Trustworthy LLM-based Agents
- 训练时间：2026-01-15
Load
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
base_model = "Qwen/Qwen3-8B"
adapter_repo = "GuQ1ng/TrajAD-Qwen3-8B-Adapter"
tokenizer = AutoTokenizer.from_pretrained(adapter_repo)
base = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype="auto",
device_map="auto"
)
model = PeftModel.from_pretrained(base, adapter_repo)
- Task
- Text Generation
- Library
- peft
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026