File size: 576 Bytes
f471413 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 |
---
license: apache-2.0
---
# GATEAU-LLaMA-7B-5K-10K
A simple demo for the deployment of the model:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("ssz1111/GATEAU-5k-10k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ssz1111/GATEAU-5k-10k", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
model = model.eval()
query = "\n\n Hello."
response, history = model.chat(tokenizer, query, history=[], max_new_tokens=512, temperature=1)
print(response)
``` |