Added gradio

README.md

@@ -1,5 +1,5 @@
 ---
-title: Typhoon-7b-q4-bnb Cuda
+title: typhoon-7b-q4-bnb_cuda
 emoji: 🏃
 colorFrom: gray
 colorTo: red

app.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python
+
+import os
+from threading import Thread
+from typing import Iterator
+
+import gradio as gr
+import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+DESCRIPTION = "# Typhoon 7B via 4-bits Quantization"
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 128
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+if torch.cuda.is_available():
+    model_id = "bandhit/typhoon-7b-q4-bnb_cuda-ts-1703352224"
+    model = AutoModelForCausalLM.from_pretrained(model_id)
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.pad_token_id = tokenizer.eos_token_id
+
+@spaces.GPU
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    max_new_tokens: int = 128,
+    temperature: float = 0.7,
+    top_p: float = 0.95,
+    top_k: int = 50,
+    repetition_penalty: float = 1.3,
+) -> Iterator[str]:
+    conversation = []
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+
+    chat_template = "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = '' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}"
+    input_ids = tokenizer.apply_chat_template(conversation, chat_template, 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=20.0, 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()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
+
+
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    additional_inputs=[
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.7,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.95,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.3,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["ชีวิตคืออะไร?"],
+        ["ความหมายของชีวิตคืออะไร?"],
+    ],
+)
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+    )
+    chat_interface.render()
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()

requirements.txt

@@ -0,0 +1,11 @@
+accelerate==0.25.0
+bitsandbytes==0.41.3
+gradio==4.9.0
+protobuf==4.23.4
+scipy==1.11.4
+sentencepiece==0.1.99
+spaces==0.18.0
+torch==2.1.2
+#transformers==4.37.0.dev0
+transformers @ git+https://github.com/huggingface/transformers
+

style.css

@@ -0,0 +1,16 @@
+h1 {
+  text-align: center;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+
+.contain {
+  max-width: 900px;
+  margin: auto;
+  padding-top: 1.5rem;
+}