Spaces:
Sleeping
Sleeping
File size: 2,610 Bytes
99dc488 66c19f0 46fd668 2cb48ed 66c19f0 46fd668 99dc488 2cb48ed 66c19f0 1ac11cc 66c19f0 46fd668 |
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 |
import os
import subprocess
import torch
import gradio as gr
from huggingface_hub import InferenceClient
from vllm.config import DeviceConfig
from vllm import LLM
from sal.models.reward_models import RLHFFlow
if not os.path.exists("search-and-learn"):
subprocess.run(["git", "clone", "https://github.com/huggingface/search-and-learn"])
subprocess.run(["pip", "install", "-e", "./search-and-learn[dev]"])
device_config = DeviceConfig(device=torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
print('device_config', device_config)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('device', device)
model_path = "meta-llama/Llama-3.2-1B-Instruct"
prm_path = "RLHFlow/Llama3.1-8B-PRM-Deepseek-Data"
llm = LLM(
model=model_path,
gpu_memory_utilization=0.5, # Utilize 50% of GPU memory
enable_prefix_caching=True, # Optimize repeated prefix computations
seed=42, # Set seed for reproducibility
)
"""
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
"""
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 = ""
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
"""
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()
|