Update main.py

main.py

@@ -6,44 +6,7 @@ import prompt_style
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-# **************************************************
-# import transformers
-# import torch
-
-# pipeline = transformers.pipeline(
-#     "text-generation",
-#     model=model_id,
-#     model_kwargs={"torch_dtype": torch.bfloat16},
-#     device_map="auto",
-# )
-
-def generate_1(item: Item):
-    messages = [
-        {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
-        {"role": "user", "content": "Who are you?"},
-    ]
-    
-    terminators = [
-        pipeline.tokenizer.eos_token_id,
-        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
-    ]
-    
-    outputs = pipeline(
-        messages,
-        max_new_tokens=item.max_new_tokens,
-        eos_token_id=terminators,
-        do_sample=True,
-        temperature=item.temperature,
-        top_p=item.top_p,
-    )
-    return outputs[0]["generated_text"][-1]
-
-# **************************************************
-
-
-
-
-client = InferenceClient(model_id)
+# client = InferenceClient(model_id)
 
 class Item(BaseModel):
     prompt: str