Upload app.py

app.py

@@ -91,15 +91,17 @@ def instruct_generate(
     encoded = tokenizer.encode(prompt, bos=True, eos=False, device=model.device)
     # prompt_length = encoded.size(0)
 
-    y = generate(
-        model,
-        idx=encoded,
-        max_seq_length=max_new_tokens,
-        max_new_tokens=max_new_tokens,
-        temperature=temperature,
-        top_k=top_k,
-        eos_id=tokenizer.eos_id
-    )
+    # y = generate(
+    #     model,
+    #     idx=encoded,
+    #     max_seq_length=max_new_tokens,
+    #     max_new_tokens=max_new_tokens,
+    #     temperature=temperature,
+    #     top_k=top_k,
+    #     eos_id=tokenizer.eos_id
+    # )
+
+    y = generate(model, encoded, max_new_tokens, temperature=temperature, top_k=top_k, eos_id=tokenizer.eos_id)
 
     output = tokenizer.decode(y)
     output = output.split("### Response:")[1].strip()