PEFT
Persian
English
iamshnoo librarian-bot commited on
Commit
1fe39a3
1 Parent(s): ea9105e

Librarian Bot: Add base_model information to model (#1)

Browse files

- Librarian Bot: Add base_model information to model (fa6ab54b4ed541d67a679c8e4afecff1c6039ae9)


Co-authored-by: Librarian Bot (Bot) <[email protected]>

Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -1,13 +1,14 @@
1
  ---
2
- library_name: peft
3
- license: cc-by-4.0
4
- datasets:
5
- - iamshnoo/alpaca-cleaned-persian
6
  language:
7
  - fa
8
  - en
 
 
 
 
9
  metrics:
10
  - accuracy
 
11
  ---
12
 
13
  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).
 
1
  ---
 
 
 
 
2
  language:
3
  - fa
4
  - en
5
+ license: cc-by-4.0
6
+ library_name: peft
7
+ datasets:
8
+ - iamshnoo/alpaca-cleaned-persian
9
  metrics:
10
  - accuracy
11
+ base_model: meta-llama/Llama-2-13b-hf
12
  ---
13
 
14
  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).