Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "mzbac/Phi-3-mini-4k-grammar-correction"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{
"role": "user",
"content": "Please correct, polish, or translate the text delimited by triple backticks to standard English.",
},
{
"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("<|end|>")]
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))
# <s><|user|> Please correct, polish, or translate the text delimited by triple backticks to standard English.<|end|><|assistant|>
# <|user|> Text=```neither 经理或员工 has been informed about the meeting```<|end|>
# <|assistant|> Output=Neither the manager nor the employee has been informed about the meeting.<|end|>
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.