sade-adrien commited on
Commit
911e1b1
1 Parent(s): 5c90c6d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -19,7 +19,9 @@ It achieves the following results on the evaluation set:
19
 
20
  ## Model description
21
 
22
- More information needed
 
 
23
 
24
  ## Intended uses & limitations
25
 
@@ -27,7 +29,7 @@ More information needed
27
 
28
  ## Training and evaluation data
29
 
30
- More information needed
31
 
32
  ## Training procedure
33
 
 
19
 
20
  ## Model description
21
 
22
+ This model is a fine-tuning of Mistral-7B-Instruct-v0.1.
23
+ This FT was using a Position Interpolation factor of 0.5 (Linear RoPE scaling).
24
+ Please note that the RoPE scaling factor should be determined by L'/L where L is the pre-training max context length and L' is the new max context length. In our case, we are just making experiments (and for us we would have had L'/L = 7200/8096 > 1 which did not require any PI scaling).
25
 
26
  ## Intended uses & limitations
27
 
 
29
 
30
  ## Training and evaluation data
31
 
32
+ Data is a 9k sample from the RedPajama datset. The context is <=7200 with a decreasing exponential distribution of scale 1500.
33
 
34
  ## Training procedure
35