ttagu99 commited on
Commit
b981a22
โ€ข
1 Parent(s): 3bcf3a6

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Intel/orca_dpo_pairs
5
+ language:
6
+ - en
7
+ ---
8
+
9
+ # Model Card for mncai/mistral-7b-dpo-v6
10
+
11
+ ### Introduction of MindsAndCompany
12
+
13
+ https://mnc.ai/
14
+
15
+ We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing Enterprise AGI (Artificial General Intelligence).
16
+
17
+ ### Model Summary
18
+ based mistral-7b, dpo tuned.
19
+
20
+
21
+ ### How to Use
22
+ Here give some examples of how to use our model.
23
+
24
+ ```python
25
+ from transformers import AutoConfig, AutoModel, AutoTokenizer
26
+ import transformers
27
+ import torch
28
+ hf_model = 'mncai/mistral-7b-dpo-v6'
29
+ message = "<|user|>\n๋‘ ๊ฐœ์˜ ๊ตฌ๊ฐ€ ์žˆ๋Š”๋ฐ ๊ฐ๊ฐ ์ง€๋ฆ„์ด 1, 2์ผ๋•Œ ๊ตฌ์˜ ๋ถ€ํ”ผ๋Š” ๋ช‡๋ฐฐ ์ฐจ์ด๊ฐ€ ๋‚˜์ง€? ์„ค๋ช…๋„ ๊ฐ™์ด ํ•ด์ค˜.\n<|assistant|>\n"
30
+
31
+ sequences = pipeline(
32
+ message,
33
+ do_sample=True,
34
+ top_k=10,
35
+ num_return_sequences=1,
36
+ eos_token_id=tokenizer.eos_token_id,
37
+ max_length=2048,
38
+ )
39
+ for seq in sequences:
40
+ print(f"Result: {seq['generated_text']}")
41
+ ```
42
+
43
+
44
+ ### Contact
45
+ If you have any questions, please raise an issue or contact us at [email protected]