tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(config): Set eos/bos to tokenizer if different (#801)

Browse Source 
* fix(config): Set eos/bos to tokenizer if different

* chore: fix lint
This commit is contained in:
NanoCode012
2023-10-29 21:32:37 +09:00
committed by GitHub
parent 827ec3d274
commit 637ed095a0
1 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/axolotl/utils/models.py
View File

@@ -386,6 +386,20 @@ def load_model(
) )
model.config.max_position_embeddings = cfg.sequence_len model.config.max_position_embeddings = cfg.sequence_len
if (
hasattr(model.config, "bos_token_id")
and model.config.bos_token_id
and model.config.bos_token_id != tokenizer.bos_token_id
):
model.config.bos_token_id = tokenizer.bos_token_id
if (
hasattr(model.config, "eos_token_id")
and model.config.eos_token_id
and model.config.eos_token_id != tokenizer.eos_token_id
):
model.config.eos_token_id = tokenizer.eos_token_id
if model.device.type == "cuda": if model.device.type == "cuda":
log_gpu_memory_usage(LOG, "after model load", model.device) log_gpu_memory_usage(LOG, "after model load", model.device)