msr2000 commited on
Commit
3290c7a
1 Parent(s): 799c814

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +57 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: deepseek
4
+ license_link: LICENSE
5
+ ---
6
+
7
+ <p align="center">
8
+ <img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
9
+ </p>
10
+ <p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
11
+ <hr>
12
+
13
+
14
+
15
+
16
+ ### 1. Introduction of Deepseek LLM
17
+
18
+ Introducing DeepSeek LLM, an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. In order to foster research, we have made DeepSeek LLM 7B/67B Base and DeepSeek LLM 7B/67B Chat open source for the research community.
19
+
20
+
21
+ ### 2. Model Summary
22
+ deepseek-llm-67b-base is a 67B parameter model with Multi-Head Attention trained on 2 trillion tokens from scratch.
23
+ - **Home Page:** [DeepSeek](https://deepseek.com/)
24
+ - **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
25
+ - **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)
26
+
27
+
28
+ ### 3. How to Use
29
+ Here give some examples of how to use our model.
30
+ #### Text Completion
31
+ ```python
32
+ import torch
33
+ from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
34
+
35
+ model_name = "deepseek-ai/deepseek-llm-67b-base"
36
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
37
+ model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
38
+ model.generation_config = GenerationConfig.from_pretrained(model_name)
39
+ model.generation_config.pad_token_id = model.generation_config.eos_token_id
40
+
41
+ text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
42
+ inputs = tokenizer(text, return_tensors="pt")
43
+ outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
44
+
45
+ result = tokenizer.decode(outputs[0], skip_special_tokens=True)
46
+ print(result)
47
+ ```
48
+
49
+ ### 4. License
50
+ This code repository is licensed under the MIT License. The use of DeepSeek LLM models is subject to the Model License. DeepSeek LLM supports commercial use.
51
+
52
+ See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL) for more details.
53
+
54
+ ### 5. Contact
55
+
56
+ If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
57
+