Update app.py

app.py

@@ -1,5 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
 """
 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
@@ -7,57 +9,29 @@ For more information on `huggingface_hub` Inference API support, please check th
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
-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 = ""
+model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4",
+                                             device_map="auto",
+                                             attn_implementation="flash_attention_2",
+                                             torch_dtype=torch.bfloat16)
 
-    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
+tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
+from transformers import  AutoTokenizer, pipeline
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+prompts = [
+    "В чем разница между фруктом и овощем?",
+    "Годы жизни колмагорова?"]
 
-        response += token
-        yield response
+def test_inference(prompt):
+    prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
+    print(prompt)
+    outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
+    return outputs[0]['generated_text'][len(prompt):].strip()
 
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+for prompt in prompts:
+    print(f"    prompt:\n{prompt}")
+    print(f"    response:\n{test_inference(prompt)}")
+    print("-"*50)