wangru8080/Lingxi-0.4B-Instruct

灵犀大模型-0.4B，V1版本，过程详见：https://github.com/wangru8080/LLM_Trainer
2024.10.30 更新model参数权重

Quickstart

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "wangru8080/Lingxi-0.4B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

prompt = "介绍北京"
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]