Spaces:
Sleeping
Sleeping
File size: 3,880 Bytes
de77006 73f7de1 de77006 73f7de1 de77006 73f7de1 de77006 73f7de1 a485913 73f7de1 de77006 73f7de1 9bea0be 73f7de1 de77006 73f7de1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
import os
from threading import Thread
from typing import Iterator
import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
DESCRIPTION = """\
# CataLlama-v0.1 Chat
This Space demonstrates model [CataLlama-v0.1-Instruct-DPO](https://huggingface.co/catallama/CataLlama-v0.1-Instruct-DPO).
CataLlama is a fine-tune on Llama-3 8B to enhance it's proficiency on the Catalan Language.
"""
if not torch.cuda.is_available():
DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
if torch.cuda.is_available():
model_id = "catallama/CataLlama-v0.1-Instruct-DPO"
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)
@spaces.GPU
def generate(
message: str,
chat_history: list[tuple[str, str]],
system_prompt: str,
max_new_tokens: int = 1024,
temperature: float = 0.6,
top_p: float = 0.9,
top_k: int = 50,
repetition_penalty: float = 1.2,
) -> Iterator[str]:
conversation = []
if system_prompt:
conversation.append({"role": "system", "content": system_prompt})
for user, assistant in chat_history:
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()
outputs = []
for text in streamer:
outputs.append(text)
yield "".join(outputs)
"""
client = InferenceClient("catallama/CataLlama-v0.1-Instruct-DPO")
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(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
"""
chat_interface = gr.ChatInterface(
fn=generate,
additional_inputs=[
gr.Textbox(value="Ets un chatbot amigable.", 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)",
),
],
)
with gr.Blocks() as demo:
gr.Markdown(DESCRIPTION)
chat_interface.render()
if __name__ == "__main__":
demo.launch() |