jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Bug] Remove prefix bos_token from messages when using lmdeploy as the accelerator (#1623)

Browse Source 
* remove prefix bos_token from messages when using lmdeploy as the accelerator

* update
This commit is contained in:
Lyu Han 2024-10-19 20:03:47 +08:00 committed by GitHub
parent b89c7b2fc3
commit 6e8adf5221
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
opencompass/models/turbomind_with_tf_above_v4_33.py
View File

@ -102,7 +102,13 @@ class TurboMindModelwithChatTemplate(BaseModel):
messages = _format_with_fast_chat_template(messages, self.fastchat_template) messages = _format_with_fast_chat_template(messages, self.fastchat_template)
else: else:
messages = [self.tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=False) for m in messages] messages = [self.tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=False) for m in messages]
# LMDeploy tokenize prompts by AutoTokenizer with its default parameter "add_special_token=True"
# OC add bos_token in the prompt, which requires tokenizing prompts using "add_speicial_token=False"
# But LMDeploy doesn't have "add_speicial_token" in the pipeline API. So, we remove bos_token
# from messages as a workaround
if self.tokenizer.bos_token:
bos_token = self.tokenizer.bos_token
messages = [message.removeprefix(bos_token) if message.startswith(bos_token) else message for message in messages]
stop_words = list(set(self.stop_words + stopping_criteria)) stop_words = list(set(self.stop_words + stopping_criteria))
DEFAULT_GEN_CONFIG = { DEFAULT_GEN_CONFIG = {
@ -129,8 +135,7 @@ class TurboMindModelwithChatTemplate(BaseModel):
results = [] results = []
outputs = self.pipe(messages, gen_config=gen_config, do_preprocess=False) outputs = self.pipe(messages, gen_config=gen_config, do_preprocess=False)
for output in outputs: for output in outputs:
text = self.tokenizer.decode(output.token_ids) results.append(output.text)
results.append(text)
for s in stop_words: for s in stop_words:
results = [r.split(s)[0] for r in results] results = [r.split(s)[0] for r in results]
@ -162,4 +167,4 @@ class TurboMindModelwithChatTemplate(BaseModel):
else: else:
filtered = {k: v for k, v in engine_config.items() if hasattr(PytorchEngineConfig, k)} filtered = {k: v for k, v in engine_config.items() if hasattr(PytorchEngineConfig, k)}
backend_config = PytorchEngineConfig(**filtered) backend_config = PytorchEngineConfig(**filtered)
return pipeline(model_path, backend_config=backend_config, log_level='INFO', max_log_len=10) return pipeline(model_path, backend_config=backend_config, log_level='WARNING')