Update app.py

app.py

@@ -1,64 +1,40 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("NLPnorth/snakmodel-7b-instruct")
-
-
-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(
+def chat(prompt):
+    messages = [
+        {"role": "system", "content": "Du er Snakmodel, skabt af IT-Universitetet i København. Du er en hjælpsom assistent."},
+        {"role": "user", "content": prompt}
+    ]
+    text = tokenizer.apply_chat_template(
         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="Du er Snakmodel, skabt af IT-Universitetet i København. Du er en hjælpsom assistent.", 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)",
-        ),
-    ],
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=20
+    )
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+    
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    
+    return response
+
+model_name = "NLPnorth/snakmodel-7b-instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto",
+    low_cpu_mem_usage=True,
 )
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo = gr.Interface(fn=chat, inputs="text", outputs="text")
+demo.launch()