Skip to content

GitLab

Unverified Commit 915b4652 authored by Camille Zhong's avatar Camille Zhong Committed by GitHub
Browse files

[doc] Update README.md of Colossal-LLAMA2 (#5233) 

* Update README.md

* Update README.md
parent d992b559
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
applications/Colossal-LLaMA-2/README.md
View file @ 915b4652
...@@ -216,6 +216,7 @@ inputs = inputs.to('cuda:0') ...@@ -216,6 +216,7 @@ inputs = inputs.to('cuda:0')
pred = model.generate(**inputs, pred = model.generate(**inputs,
max_new_tokens=256, max_new_tokens=256,
do_sample=True, do_sample=True,
temperature=0.3,
top_k=50, top_k=50,
top_p=0.95, top_p=0.95,
num_return_sequences=1) num_return_sequences=1)
...@@ -238,7 +239,7 @@ generation_kwargs = {"max_new_tokens": 256, ...@@ -238,7 +239,7 @@ generation_kwargs = {"max_new_tokens": 256,
"temperature": 0.3 "temperature": 0.3
} }
input = '离离原上草，\n\n->\n\n' input = '明月松间照，\n\n->\n\n'
inputs = tokenizer(input, return_token_type_ids=False, return_tensors='pt') inputs = tokenizer(input, return_token_type_ids=False, return_tensors='pt')
inputs = inputs.to('cuda:0') inputs = inputs.to('cuda:0')
output = model.generate(**inputs, **generation_kwargs) output = model.generate(**inputs, **generation_kwargs)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment