base_model, inference, license, model_creator, model_name, pipeline_tag, quantized_by, tags

base_model	inference	license	model_creator	model_name	pipeline_tag	quantized_by	tags
mzbac/Phi-3-mini-4k-grammar-correction	true	mit	mzbac	Phi-3-mini-4k-grammar-correction	text-generation	afrideva	gguf ggml quantized

Phi-3-mini-4k-grammar-correction-GGUF

Quantized GGUF model files for Phi-3-mini-4k-grammar-correction from mzbac

Original Model Card:

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|>