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

fix(example): set model_type to load for gemma3 text (#3242)

Browse Source 
* fix: set model_type to load for gemma3 text

* chore: simplify

* chore: unify
This commit is contained in:
NanoCode012
2025-11-04 07:35:07 +07:00
committed by GitHub
parent ed58fa8a75
commit 26f05b6008
3 changed files with 9 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/gemma3/gemma-3-1b-qlora.yml
View File

@@ -1,7 +1,7 @@
base_model: google/gemma-3-1b-it
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
model_type: Gemma3ForCausalLM
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

6
examples/gemma3/gemma-3-270m-qlora.yml
View File

@@ -1,7 +1,7 @@
base_model: google/gemma-3-270m-it
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
model_type: Gemma3ForCausalLM
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

3
examples/gemma3/gemma-3-4b-qlora.yml
View File

@@ -1,5 +1,8 @@
base_model: google/gemma-3-4b-it
# Need to set else transformers tries to load vision too
model_type: Gemma3ForCausalLM
load_in_4bit: true
# gemma3 doesn't seem to play nice with ddp