ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

max_seq_length

Browse source
This commit is contained in:
Daniel Han 2025-03-10 04:39:25 -07:00
commit 5d8b756ca7
2 changed files with 9 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
unsloth/models/llama.py
View file

@ -1913,12 +1913,12 @@ class FastLlamaModel:
# Save max_seq_length
model.max_seq_length = max_seq_length
internal_model = model
while hasattr(internal_model, "model"):
internal_model.max_seq_length = max_seq_length
internal_model = internal_model.model
m = model
while hasattr(m, "model"):
m.max_seq_length = max_seq_length
m = m.model
pass
internal_model.max_seq_length = max_seq_length
m.max_seq_length = max_seq_length
# We check the tokenizer first for errors
if fix_tokenizer:

5
unsloth/models/vision.py
View file

@ -238,11 +238,13 @@ class FastBaseModel:
tokenizer.tokenizer.padding_side = "left" # Force inference
m = model
while hasattr(m, "model"):
m.max_seq_length = max_seq_length
m._saved_temp_tokenizer = tokenizer
# Also set is_loaded_in_8bit to disable incorrect DDP
m.is_loaded_in_8bit = True if not full_finetuning else False
m = m.model
pass
m.max_seq_length = max_seq_length
m._saved_temp_tokenizer = tokenizer
# Also set is_loaded_in_8bit to disable incorrect DDP
m.is_loaded_in_8bit = True if not full_finetuning else False
@ -328,7 +330,7 @@ class FastBaseModel:
gc.collect()
torch.cuda.empty_cache()
pass
max_seq_length = model.max_seq_length
lora_config = LoraConfig(
r = r,
lora_alpha = lora_alpha,
@ -346,6 +348,7 @@ class FastBaseModel:
requires_grad_for_gradient_checkpointing(model)
model = FastBaseModel.post_patch_model(model, use_gradient_checkpointing)
model.max_seq_length = max_seq_length
# Clear deleted GPU items
for _ in range(3):