Skip to content

Commit

Permalink
fastllm
Browse files Browse the repository at this point in the history
  • Loading branch information
YerongLi committed Jul 11, 2023
1 parent 5745e21 commit 2e4891c
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion src/cli_demo.py
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def main():
global stop_stream
model_args, finetuning_args, generating_args = prepare_infer_args()
model, tokenizer = load_pretrained(model_args, finetuning_args)
model = llm.from_hf(model, tokenizer, dtype = "float16") # dtype支持float16, float32, float64, int32, int64, bool
model = llm.from_hf(model, tokenizer, dtype = "int4") # dtype支持float16, float32, float64, int32, int64, bool

if torch.cuda.device_count() > 1:
from accelerate import dispatch_model
Expand Down

0 comments on commit 2e4891c

Please sign in to comment.