File size: 1,763 Bytes
aed786e 4e35316 aed786e 4e35316 aed786e 9b71440 aed786e 9b71440 aed786e 4e35316 9b71440 aed786e 9b71440 aed786e 9b71440 |
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 |
import os
import gradio as gr
from huggingface_hub import InferenceClient
import requests
url = "https://huggingface.co/models-json?num_parameters=min%3A128B&inference_provider=cerebras%2Cnebius%2Cfireworks-ai%2Ctogether%2Csambanova%2Cnovita%2Cgroq%2Cnscale%2Chyperbolic%2Cfeatherless-ai%2Cfal-ai%2Ccohere%2Creplicate%2Chf-inference&sort=trending&withCount=true"
res = requests.get(url).json()
model_ids = [m['id'] for m in res.get('models', [])]
client = InferenceClient(provider="novita", api_key=os.environ["HF_TOKEN"])
#models = ["deepseek-ai/DeepSeek-V3.1","zai-org/GLM-4.5","Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-R1-0528","Qwen/Qwen3-Next-80B-A3B-Thinking"]
def respond(message, history, model):
history.append((message, ""))
yield "", history
full_reply = ""
for chunk in client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": message}],
stream=True
):
if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content:
full_reply += chunk.choices[0].delta.content
history[-1] = (message, full_reply)
yield "", history
with gr.Blocks() as demo:
gr.Markdown("## AI")
chatbot = gr.Chatbot(height=400)
msg = gr.Textbox(label="Ask me smth")
model_dd = gr.Dropdown(model_ids, label="Model", value=models[0])
with gr.Row():
submit_btn = gr.Button("Send")
clear = gr.Button("Clear")
msg.submit(respond, [msg, chatbot, model_dd], [msg, chatbot])
submit_btn.click(respond, [msg, chatbot, model_dd], [msg, chatbot])
clear.click(lambda: None, None, chatbot, queue=False)
demo.queue().launch() |