SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Llama] remove prompt and fix prefix finetuning (#25565)

Browse Source 
* nit

* update

* make sure use_default_system_prompt is saved

* update checkpointing

* consistency

* use_default_system_prompt for test
This commit is contained in:
Arthur
2023-08-18 13:39:23 +02:00
committed by GitHub
parent 30b3c46ff5
commit bc3e20dcf0
4 changed files with 37 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/pipelines/test_pipelines_conversational.py
View File

@@ -220,7 +220,7 @@ class ConversationalPipelineTests(unittest.TestCase):
@require_torch
@slow
def test_integration_torch_conversation_llama2_input_ids(self):
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", use_default_system_prompt=True)
conversation = Conversation(
"What is so great about #1?",