Hugging Face's logo

nkpz
/
llama2-22b-blocktriangular-alpaca

Text Generation
Transformers
Safetensors
llama
Inference Endpoints
text-generation-inference
Model card Files Community
nkpz commited on
Commit
1851ed9
•
1 Parent(s): 312879a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ license: other
5
 
6
  https://huggingface.co/chargoddard/llama2-22b-blocktriangular trained one one epoch of 52k rows of Stanford Alpaca. About 11 hours on a 3090.
7
 
8
- I had trouble with training using the other 22b method with `BLOCK_DIAGONAL=True`, but with this method, this is the first time I've been able to target all modules without breaking the output.
9
 
10
  `target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "up_proj", "gate_proj", "down_proj"]`
11
 
 
5
 
6
  https://huggingface.co/chargoddard/llama2-22b-blocktriangular trained one one epoch of 52k rows of Stanford Alpaca. About 11 hours on a 3090.
7
 
8
+ I had trouble with training using the other 22b method with `BLOCK_DIAGONAL=True` as done in https://huggingface.co/chargoddard/llama2-22b, but with this method, this is the first time I've been able to target all modules without breaking the output.
9
 
10
  `target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "up_proj", "gate_proj", "down_proj"]`
11