iamshnoo commited on
Commit
28b644e
1 Parent(s): 436ff13

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -1,6 +1,18 @@
1
  ---
2
  library_name: peft
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
4
  ## Training procedure
5
 
6
 
@@ -17,4 +29,4 @@ The following `bitsandbytes` quantization config was used during training:
17
  ### Framework versions
18
 
19
 
20
- - PEFT 0.4.0
 
1
  ---
2
  library_name: peft
3
+ license: cc-by-4.0
4
+ datasets:
5
+ - yahma/alpaca-cleaned
6
+ language:
7
+ - en
8
+ metrics:
9
+ - accuracy
10
  ---
11
+
12
+ This represents the PEFT weights only. The base model is LLaMA 2. Instruction finetuning was done using 4 bit QLoRA on a single A100 GPU with the PEFT config as given below. The dataset used for this instruction finetuning process is a translated version of the cleaned alpaca dataset (translated using NLLB-1.3B).
13
+
14
+ Do note that this model might have inferior performance on some language specific tasks compared to full finetuning or a different base model trained with more language specific data.
15
+
16
  ## Training procedure
17
 
18
 
 
29
  ### Framework versions
30
 
31
 
32
+ - PEFT 0.4.0