15 lines
301 B
Markdown
15 lines
301 B
Markdown
|
---
|
||
|
|
frameworks:
|
||
|
|
- ""
|
||
|
|
---
|
||
|
|
# Qwen3-1.7B-GPU-QA-Lora
|
||
|
|
|
||
|
|
基于Qwen3-1.7B使用LoRA微调的GPU并行计算问答模型。
|
||
|
|
|
||
|
|
## 使用方法
|
||
|
|
```python
|
||
|
|
from modelscope import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_id = "hyx990604/Qwen3-1.7B-GPU-QA-Lora"
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(model
|