Azure99 commited on
Commit
83ae9be
1 Parent(s): d6644a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -3
README.md CHANGED
@@ -1,3 +1,44 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Azure99/blossom-chat-v3
5
+ - Azure99/blossom-math-v4
6
+ - Azure99/blossom-wizard-v3
7
+ - Azure99/blossom-orca-v3
8
+ language:
9
+ - zh
10
+ - en
11
+ ---
12
+ # **BLOSSOM-v5.1-9b**
13
+
14
+ [💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)
15
+
16
+ ### Introduction
17
+
18
+ Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Yi-1.5-9B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source.
19
+
20
+ Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs.
21
+
22
+ ### Inference
23
+
24
+ Inference is performed in the form of dialogue continuation.
25
+
26
+ Single-turn dialogue
27
+
28
+ ```
29
+ A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
30
+ |Human|: hello
31
+ |Bot|:
32
+ ```
33
+
34
+ Multi-turn dialogue
35
+
36
+ ```
37
+ A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
38
+ |Human|: hello
39
+ |Bot|: Hello! How can I assist you today?<|endoftext|>
40
+ |Human|: Generate a random number using python
41
+ |Bot|:
42
+ ```
43
+
44
+ Note: At the end of the Bot's output in the historical conversation, append a `<|endoftext|>`.