Sentdex
/

Walls1337bot-Llama2-7B-003.004.700

Text Generation

Model card Files Files and versions Community

Sentdex commited on Mar 1

Commit

574b9c0

•

1 Parent(s): 7cdb1f5

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -24,6 +24,5 @@ prompt = "Your text here."
 formatted_prompt = f"### BEGIN CONVERSATION ###\n\n## Speaker_0: ##\n{prompt}\n\n## Walls1337bot: ##\n"
 inputs = tokenizer(formatted_prompt, return_tensors="pt")
 outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=128)
-text_output =
 print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0])
 ```

 formatted_prompt = f"### BEGIN CONVERSATION ###\n\n## Speaker_0: ##\n{prompt}\n\n## Walls1337bot: ##\n"
 inputs = tokenizer(formatted_prompt, return_tensors="pt")
 outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=128)
 print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0])
 ```