Skip to content

Fixup #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fixup #12

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3c1b20e
Fix bug to use all CPU cores
Sep 27, 2024
b3c12a1
Define device in text_completion
Sep 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,6 @@ def build(checkpoints_dir: str, tokenizer_path: str, load_model: bool, max_seq_l

if device == "cuda":
torch.set_default_tensor_type(torch.cuda.HalfTensor)
else:
torch.set_default_tensor_type(torch.BFloat16Tensor)

model = Transformer(model_args).to(device)

Expand All @@ -56,6 +54,7 @@ def build(checkpoints_dir: str, tokenizer_path: str, load_model: bool, max_seq_l
return LLaMA(model, tokenizer, model_args)

def text_completion(self, prompts: list[str], temperature: float = 0.6, top_p: float = 0.9, max_gen_len: Optional[int] = None):
device = self.args.device
if max_gen_len is None:
max_gen_len = self.args.max_seq_len - 1
# Convert each prompt into tokens
Expand Down Expand Up @@ -156,7 +155,7 @@ def _sample_top_p(self, probs, p):
checkpoints_dir='llama-2-7b/',
tokenizer_path='tokenizer.model',
load_model=True,
max_seq_len=1024,
max_seq_len=128,
max_batch_size=len(prompts),
device=device
)
Expand Down