brildev7
/

gemma-7b-it-summarization-ko-sft-qlora

Generated from Trainer

Model card Files Files and versions Community

brildev7 commited on Mar 4

Commit

83f0140

•

1 Parent(s): 13f8fd7

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ tags:
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-model_id = "brildev7/gemma-7b-it-finetune-summarization-ko-lora"
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_compute_dtype=torch.float16,

 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+model_id = "brildev7/gemma-7b-it-finetune-summarization-ko-sft-qlora"
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_compute_dtype=torch.float16,