xusenlinzy/api-for-open-llm

💡 [REQUEST] - 请求支持幻方量化的DeepSeek LLM

Closed this issue · 1 comments

SirlyDreamer commented

起始日期 | Start Date

No response

实现PR | Implementation PR

No response

相关Issues | Reference Issues

No response

摘要 | Summary

幻方量化于近日发布 deepseek-llm-7b-chat 和 deepseek-llm-67b-chat ，烦请开发者做出适配。

基本示例 | Basic Example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "deepseek-ai/deepseek-llm-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

messages = [
    {"role": "user", "content": "Who are you?"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)

缺陷 | Drawbacks

67B模型需要多张显卡进行推理

未解决问题 | Unresolved questions

No response