File size: 1,062 Bytes
bc8a0f0 82b2db1 bc8a0f0 82b2db1 bc8a0f0 82b2db1 0a94c7d 82b2db1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
---
language:
- it
- en
license: llama3
library_name: transformers
base_model: meta-llama/Meta-Llama-3-8B
## How to Use
---
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
MODEL_NAME = "DeepMount00/Llama-3.1-Distilled"
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16).eval()
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
def generate_answer(prompt):
messages = [
{"role": "user", "content": prompt},
]
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=200, do_sample=True,
temperature=0.001)
decoded = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
return decoded[0]
prompt = "Come si apre un file json in python?"
answer = generate_answer(prompt)
print(answer)
```
---
## Developer
[Michele Montebovi]
|