stabilityai
/

stablelm-2-12b-chat

Text Generation

Inference Endpoints

Model card Files Files and versions Community

pvduy commited on 18 days ago

Commit

1a48dd5

•

1 Parent(s): 3ebcace

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -56,7 +56,6 @@ tokens = model.generate(
     max_new_tokens=100,
     temperature=0.7,
     do_sample=True,
-    eos_token_id=100278 # <|im_end|>
 )
 output = tokenizer.decode(tokens[:, inputs.shape[-1]:][0], skip_special_tokens=False)

     max_new_tokens=100,
     temperature=0.7,
     do_sample=True,
 )
 output = tokenizer.decode(tokens[:, inputs.shape[-1]:][0], skip_special_tokens=False)