tranhoangnguyen03
/

Gemma-2-9B-It-SPPO-Iter3_Q8

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

tranhoangnguyen03 commited on Jul 7

Commit

4ab6e94

•

1 Parent(s): 7ac0d05

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ from transformers import AutoTokenizer
 from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
 pretrained_model_dir = "UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3"
-quantized_model_dir = "/content/Gemma-2-9B-It-SPPO-Iter3_Q8"
 tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir)

 from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
 pretrained_model_dir = "UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3"
+quantized_model_dir = "/quantized/Gemma-2-9B-It-SPPO-Iter3_Q8"
 tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir)