Update app.py

app.py

@@ -12,35 +12,16 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Llama-2 7B Chat
-
-This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
-
-🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
-
-🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
+# MIQU-70B
 """
 
-LICENSE = """
-<p/>
-
----
-As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
-this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
+LICENSE = """Pirate license
 """
 
 if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+    DESCRIPTION += ""
 
 
-if torch.cuda.is_available():
-    model_id = "meta-llama/Llama-2-7b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    tokenizer.use_default_system_prompt = False
-
-
-@spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
@@ -58,31 +39,17 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
+    r = requests.post('https://social-warthog-fleet.ngrok-free.app/api/chat', params={
+  "model": "miqu",
+  "messages":conversation,
+  "stream": false,
+  "options":{"num_predict": 128, "temperature":1, "top_p":0.95}
+
+        })
+    outputs = [r.json()['message']['content']]
 
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
+    yield "".join(outputs)
 
 
 chat_interface = gr.ChatInterface(