deepseek-llm-67b-base

[?Homepage] | [? Chat with DeepSeek LLM] | [Discord] | [Wechat(微信)]

1. Itroductio of Deepseek LLM

Itroducig DeepSeek LLM, a advaced laguage model comprisig 67 billio parameters. It has bee traied from scratch o a vast dataset of 2 trillio tokes i both Eglish ad Chiese. I order to foster research, we have made DeepSeek LLM 7B/67B Base ad DeepSeek LLM 7B/67B Chat ope source for the research commuity.

2. Model Summary

deepseek-llm-67b-base is a 67B parameter model with Grouped-Query Attetio traied o 2 trillio tokes from scratch.

• Home Page: DeepSeek
• Repository: deepseek-ai/deepseek-LLM
• Chat With DeepSeek LLM: DeepSeek-LLM

3. How to Use

Here give some examples of how to use our model.

Text Completio

import torch
from modelscope import AutoTokeizer, AutoModelForCausalLM, GeeratioCofig

model_ame = "deepseek-ai/deepseek-llm-67b-base"
tokeizer = AutoTokeizer.from_pretraied(model_ame)
model = AutoModelForCausalLM.from_pretraied(model_ame, torch_dtype=torch.bfloat16, device_map="auto")
model.geeratio_cofig = GeeratioCofig.from_pretraied(model_ame)
model.geeratio_cofig.pad_toke_id = model.geeratio_cofig.eos_toke_id

text = "A attetio fuctio ca be described as mappig a query ad a set of key-value pairs to a output, where the query, keys, values, ad output are all vectors. The output is"
iputs = tokeizer(text, retur_tesors="pt")
outputs = model.geerate(**iputs.to(model.device), max_ew_tokes=100)

result = tokeizer.decode(outputs[0], skip_special_tokes=True)
prit(result)

4. Licese

This code repository is licesed uder the MIT Licese. The use of DeepSeek LLM models is subject to the Model Licese. DeepSeek LLM supports commercial use.

See the LICENSE-MODEL for more details.

5. Cotact

If you have ay questios, please raise a issue or cotact us at service@deepseek.com.

[?Homepage] | [? Chat with DeepSeek LLM] | [Discord] | [Wechat(微信)] 1. Introduction of Deeps