sequelbox commited on
Commit
52ce64c
1 Parent(s): 4071ec2
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -30,15 +30,21 @@ A few examples of different formats:
30
 
31
  2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
32
 
33
- 3. [INST] Good morning! Can you let me know how to parse a text file and turn the semicolons into commas? [/INST]
34
 
35
  ## The Model
36
  Shining Valiant is built on Llama 2's 70b parameter architecture. We've created the model through multiple finetuning runs on different compositions of our dataset.
37
 
38
  Our dataset is:
 
 
39
  75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
 
 
40
  25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
41
 
 
 
42
  We are actively working on expanding and improving this dataset for use in future releases of this model and others.
43
 
44
  ## Who We Are
 
30
 
31
  2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
32
 
33
+ 3. [INST] <<SYS>>You are an intelligent, helpful AI assistant.<</SYS>>Deep dive about a country with interesting history: [/INST]
34
 
35
  ## The Model
36
  Shining Valiant is built on Llama 2's 70b parameter architecture. We've created the model through multiple finetuning runs on different compositions of our dataset.
37
 
38
  Our dataset is:
39
+
40
+
41
  75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
42
+
43
+
44
  25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
45
 
46
+
47
+
48
  We are actively working on expanding and improving this dataset for use in future releases of this model and others.
49
 
50
  ## Who We Are