chainyo commited on
Commit
d417c1f
1 Parent(s): cbbe0bc

update readme

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -2,7 +2,7 @@
2
 
3
  This repository contains a LLaMA-7B fine-tuned model on the [Standford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) cleaned version dataset.
4
 
5
- I used [LLaMA-7B-hf](decapoda-research/llama-7b-hf) as a base model
6
 
7
  # Usage
8
 
@@ -17,4 +17,9 @@ model = LlamaForCausalLM.from_pretrained(
17
  load_in_8bit=True,
18
  torch_dtype=torch.float16,
19
  device_map="auto",
20
- )
 
 
 
 
 
 
2
 
3
  This repository contains a LLaMA-7B fine-tuned model on the [Standford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) cleaned version dataset.
4
 
5
+ ⚠️ **I used [LLaMA-7B-hf](decapoda-research/llama-7b-hf) as a base model, so this model is for Research purpose only (See the [license](https://huggingface.co/decapoda-research/llama-7b-hf/blob/main/LICENSE))**
6
 
7
  # Usage
8
 
 
17
  load_in_8bit=True,
18
  torch_dtype=torch.float16,
19
  device_map="auto",
20
+ )
21
+
22
+ model.eval()
23
+ if torch.__version__ >= "2":
24
+ model = torch.compile(model)
25
+ ```