protgpt3
/

ProtGPT3-MSA

Text Generation

protein-language-model

protein-generation

multiple-sequence-alignment

few-shot-prompting

homolog-conditioned-generation

mixture-of-experts

text-generation-inference

Model card Files Files and versions

protgpt3 commited on 23 days ago

Commit

e004744

·

verified ·

1 Parent(s): e298394

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -151,7 +151,7 @@ inputs = tokenizer(prompt, return_tensors="pt", padding=True).to(model.device)
 with torch.no_grad():
     output_ids = model.generate(
-        **inputs,
         max_new_tokens=512,
         do_sample=True,
         temperature=0.8,
@@ -184,7 +184,7 @@ inputs = tokenizer(prompt, return_tensors="pt", padding=True).to(model.device)
 with torch.no_grad():
     output_ids = model.generate(
-        **inputs,
         max_new_tokens=512,
         do_sample=True,
         temperature=0.8,

 with torch.no_grad():
     output_ids = model.generate(
+        inputs["input_ids"],
         max_new_tokens=512,
         do_sample=True,
         temperature=0.8,
 with torch.no_grad():
     output_ids = model.generate(
+        inputs["input_ids"],
         max_new_tokens=512,
         do_sample=True,
         temperature=0.8,