File size: 1,592 Bytes
8e80803 419bd0f 8e80803 c0fc551 8e80803 |
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 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
---
license: llama3
---
# Model
fine-tuned LLaMA 3 8B on synthetic dataset generated by GPT-4 and LLaMA 3 70B via MLX-LM
## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "mzbac/llama-3-8B-grammar-hf"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{
"role": "system",
"content": "Please correct, polish, or translate the text delimited by triple backticks to standard English.",
},
]
messages.append({"role": "user", "content":"Text=```neither 经理或员工 has been informed about the meeting```"})
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.1,
)
response = outputs[0]
print(tokenizer.decode(response))
# <|begin_of_text|><|start_header_id|>system<|end_header_id|>
# Please correct, polish, or translate the text delimited by triple backticks to standard English.<|eot_id|><|start_header_id|>user<|end_header_id|>
# Text=```neither 经理或员工 has been informed about the meeting```<|eot_id|><|start_header_id|>assistant<|end_header_id|>
# Output=Neither the manager nor the employees have been informed about the meeting.<|eot_id|>
``` |