ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Fix C-Eval ChatGLM loading issue (#10206)

Browse source 
* Add c-eval workflow and modify running files

* Modify the chatglm evaluator file

* Modify the ceval workflow for triggering test

* Modify the ceval workflow file

* Modify the ceval workflow file

* Modify ceval workflow

* Adjust the ceval dataset download

* Add ceval workflow dependencies

* Modify ceval workflow dataset download

* Add ceval test dependencies

* Add ceval test dependencies

* Correct the result print

* Fix the nightly test trigger time

* Fix ChatGLM loading issue
This commit is contained in:
Yuxuan Xia 2024-02-22 10:00:43 +08:00 committed by GitHub
parent 94cb16fe40
commit 7cbc2429a6
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
python/llm/dev/benchmark/ceval/evaluators/chatglm.py
View file

@ -22,7 +22,7 @@ from thefuzz import process
from transformers import AutoTokenizer from transformers import AutoTokenizer
from evaluators.evaluator import Evaluator from evaluators.evaluator import Evaluator
from bigdl.llm.transformers import AutoModelForCausalLM from bigdl.llm.transformers import AutoModel
from transformers.generation.utils import LogitsProcessorList from transformers.generation.utils import LogitsProcessorList
from transformers.generation.logits_process import LogitsProcessor from transformers.generation.logits_process import LogitsProcessor
@ -42,7 +42,7 @@ class ChatGLMEvaluator(Evaluator):
self.model_path, self.model_path,
trust_remote_code=True trust_remote_code=True
) )
self.model = AutoModelForCausalLM.from_pretrained( self.model = AutoModel.from_pretrained(
self.model_path, self.model_path,
load_in_low_bit=self.qtype, load_in_low_bit=self.qtype,
optimize_model=True, optimize_model=True,