Skip to content

Fix renaming on other model than Llama #2762

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 18, 2025
Merged

Fix renaming on other model than Llama #2762

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion unsloth/models/cohere.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -466,7 +466,7 @@ def pre_patch():
CohereDecoderLayer .forward = CohereDecoderLayer_fast_forward
CohereModel .forward = LlamaModel_fast_forward
CohereForCausalLM .forward = CausalLM_fast_forward(CohereModel_fast_forward_inference)
PeftModelForCausalLM .forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM .forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(CohereForCausalLM)

import transformers.models.cohere.modeling_cohere
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/gemma.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,7 +332,7 @@ def pre_patch():
GemmaDecoderLayer .forward = GemmaDecoderLayer_fast_forward
GemmaModel .forward = LlamaModel_fast_forward
GemmaForCausalLM .forward = CausalLM_fast_forward(GemmaModel_fast_forward_inference)
PeftModelForCausalLM.forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM.forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(GemmaForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/gemma2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -477,7 +477,7 @@ def pre_patch():
Gemma2DecoderLayer .forward = Gemma2DecoderLayer_fast_forward
Gemma2Model .forward = LlamaModel_fast_forward
Gemma2ForCausalLM .forward = CausalLM_fast_forward(Gemma2Model_fast_forward_inference)
PeftModelForCausalLM .forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM .forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(Gemma2ForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/granite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -468,7 +468,7 @@ def pre_patch():
GraniteModel .forward = LlamaModel_fast_forward
GraniteForCausalLM .forward = CausalLM_fast_forward(GraniteModel_fast_forward_inference)
GraniteForCausalLM .__init__ = patched_init(GraniteForCausalLM.__init__)
PeftModelForCausalLM .forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM .forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(GraniteForCausalLM)

import transformers.models.granite.modeling_granite
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/mistral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -368,7 +368,7 @@ def pre_patch():
MistralDecoderLayer .forward = LlamaDecoderLayer_fast_forward
MistralModel .forward = LlamaModel_fast_forward
MistralForCausalLM .forward = MistralForCausalLM_fast_forward
PeftModelForCausalLM .forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM .forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(MistralForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/qwen2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ def pre_patch():
Qwen2DecoderLayer .forward = LlamaDecoderLayer_fast_forward
Qwen2Model .forward = LlamaModel_fast_forward
Qwen2ForCausalLM .forward = CausalLM_fast_forward(LlamaModel_fast_forward_inference)
PeftModelForCausalLM.forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM.forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(Qwen2ForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/qwen3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,7 +387,7 @@ def pre_patch():
Qwen3DecoderLayer .forward = LlamaDecoderLayer_fast_forward
Qwen3Model .forward = LlamaModel_fast_forward
Qwen3ForCausalLM .forward = CausalLM_fast_forward(_LlamaModel_fast_forward_inference(Qwen3Attention_fast_forward_inference))
PeftModelForCausalLM.forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM.forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(Qwen3ForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down
2 changes: 1 addition & 1 deletion unsloth/models/qwen3_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,7 @@ def pre_patch():
Qwen3MoeDecoderLayer .forward = Qwen3MoeDecoderLayer_fast_forward
Qwen3MoeModel .forward = LlamaModel_fast_forward
Qwen3MoeForCausalLM .forward = CausalLM_fast_forward(LlamaModel_fast_forward_inference)
PeftModelForCausalLM.forward = PeftModelForCausalLM_fast_forward
PeftModelForCausalLM.forward = PeftModel_fast_forward
fix_prepare_inputs_for_generation(Qwen3MoeForCausalLM)

# Solves https://github.com/unslothai/unsloth/issues/168
Expand Down