updating again

app.py

@@ -1,59 +1,57 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-# Example of a freely accessible model
-client = InferenceClient("gpt-3.5-turbo")
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+from transformers import pipeline
+import torch
+
+model_id = "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+    # attn_implementation="flash_attention_2"
 )
 
-if __name__ == "__main__":
-    demo.launch()
+tokenizer = AutoTokenizer.from_pretrained(
+    model_id,
+    trust_remote_code=True
+)
+
+streamer = TextStreamer(tokenizer)
+
+pipeline = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    streamer=streamer
+)
+
+# Then you can use the pipeline to generate text.
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|im_end|>"),
+    tokenizer.convert_tokens_to_ids("<|eot_id|>") # safer to have this too
+]
+
+outputs = pipeline(
+    prompt,
+    max_new_tokens=2048,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.95,
+)
+print(outputs[0]["generated_text"][len(prompt):])