OpenVINO
/

mixtral-8x7b-instruct-v0.1-int4-ov

Text Generation

Inference Endpoints

Model card Files Files and versions Community

katuni4ka commited on Apr 1

Commit

e313eec

•

1 Parent(s): 255a3b9

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ messages = [
     {"role": "user", "content": "Do you have mayonnaise recipes?"}
 ]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
 outputs = model.generate(inputs, max_new_tokens=20)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))

     {"role": "user", "content": "Do you have mayonnaise recipes?"}
 ]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
 outputs = model.generate(inputs, max_new_tokens=20)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))