init

app.py

@@ -0,0 +1,85 @@
+import spaces
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+
+"""
+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
+"""
+model_name = "Merdeka-LLM/merdeka-llm-3.2b-128k-instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+streamer = TextIteratorStreamer(tokenizer, timeout=100., skip_prompt=True, skip_special_tokens=True)
+
+@spaces.GPU
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    # system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": "You are a professional lawyer who is familiar with Malaysia Law."}]
+
+    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 = ""
+
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+    generate_kwargs = dict(
+        model_inputs,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        streamer=streamer
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+    for new_token in streamer:
+      if new_token != '<':
+          response += new_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=0.1, 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(
+        
+    )

requirements.txt

@@ -0,0 +1,63 @@
+accelerate==1.0.1
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+fastapi==0.115.4
+ffmpy==0.4.0
+filelock==3.16.1
+fsspec==2024.10.0
+gradio==5.4.0
+gradio_client==1.4.2
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+Jinja2==3.1.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==1.26.4
+orjson==3.10.10
+packaging==24.1
+pandas==2.2.3
+pillow==11.0.0
+psutil==5.9.8
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.9.3
+ruff==0.7.1
+safehttpx==0.1.1
+safetensors==0.4.5
+semantic-version==2.10.0
+setuptools==75.3.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+spaces==0.30.4
+starlette==0.41.2
+sympy==1.13.1
+tokenizers==0.20.1
+tomlkit==0.12.0
+torch==2.2.0
+tqdm==4.66.6
+transformers==4.46.1
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+websockets==12.0