torchao-dev
/

opt-125m-float8dq-row-0.13-dev

Text Generation

text-generation-inference

Model card Files Files and versions

Update README.md

#1

by jerryzh168 - opened Jul 14

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 # Push to hub
 USER_ID = "torchao-testing"
 MODEL_NAME = model_id.split("/")[-1]
-save_to = f"{USER_ID}/{MODEL_NAME}-int4wo-preshuffled-0.13-dev"
 quantized_model.push_to_hub(save_to, safe_serialization=False)
 tokenizer.push_to_hub(save_to)

 # Push to hub
 USER_ID = "torchao-testing"
 MODEL_NAME = model_id.split("/")[-1]
+save_to = f"{USER_ID}/{MODEL_NAME}-float8dq-row-0.13-dev"
 quantized_model.push_to_hub(save_to, safe_serialization=False)
 tokenizer.push_to_hub(save_to)