mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-05 15:46:16 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore(style): reduce line length and truncate compression

Browse Source 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
aarnphm-ec2-dev
2023-08-22 17:02:00 +00:00
parent bc851b1d13
commit eddbc06374
67 changed files with 1661 additions and 301 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
openllm-python/src/openllm/models/opt/modeling_opt.py
View File

@@ -14,4 +14,7 @@ class OPT(openllm.LLM["transformers.OPTForCausalLM", "transformers.GPT2Tokenizer
def generate(self, prompt: str, **attrs: t.Any) -> list[str]:
import torch
with torch.inference_mode():
return self.tokenizer.batch_decode(self.model.generate(**self.tokenizer(prompt, return_tensors="pt").to(self.device), do_sample=True, generation_config=self.config.model_construct_env(**attrs).to_generation_config()), skip_special_tokens=True)
return self.tokenizer.batch_decode(
self.model.generate(**self.tokenizer(prompt, return_tensors="pt").to(self.device), do_sample=True, generation_config=self.config.model_construct_env(**attrs).to_generation_config()),
skip_special_tokens=True
)