|
--- |
|
library_name: transformers |
|
datasets: |
|
- LooksJuicy/ruozhiba |
|
--- |
|
## 项目介绍 |
|
- 显卡：T4 |
|
- 模型：Llama3-8B |
|
- 数据集：LooksJuicy/ruozhiba |
|
- 微调方法：QLoRA |
|
|
|
## 使用方法 |
|
``` |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_name = "snowfly/Llama-3-8B-QLoRA-ruozhiba" |
|
|
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
|
|
|
text = "### Human:如何写代码? ### Assistant:" |
|
device = "cuda:0" |
|
|
|
inputs = tokenizer(text, return_tensors="pt").to(device) |
|
|
|
|
|
outputs = model.generate(**inputs, max_new_tokens=50) |
|
|
|
|
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
