Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
File size: 3,041 Bytes
1660171 |
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 |
import gradio as gr
from gradio_huggingfacehub_search import HuggingfaceHubSearch
import requests
processed_inputs = {}
def process_inputs(markdown, model_id, q_method, email, oauth_token: gr.OAuthToken | None, profile: gr.OAuthProfile | None):
if oauth_token is None or oauth_token.token is None or profile.username is None:
return "##### You must be logged in to use this service."
if not model_id or not q_method or not email:
return "##### All fields are required!"
input_hash = hash((model_id, q_method, oauth_token.token, profile.username))
if input_hash in processed_inputs and processed_inputs[input_hash] == 200:
return "##### This request has already been submitted successfully. Please do not submit the same request multiple times."
url = "https://sdk.nexa4ai.com/task"
data = {
"repository_url": f"https://huggingface.co/{model_id}",
"username": profile.username,
"access_token": oauth_token.token,
"email": email,
"quantization_option": q_method,
}
response = requests.post(url, json=data)
if response.status_code == 200:
processed_inputs[input_hash] = 200
return "##### Your request has been submitted successfully. We will notify you by email once processing is complete. There is no need to submit the same request multiple times."
else:
processed_inputs[input_hash] = response.status_code
return f"##### Failed to submit request: {response.text}"
iface = gr.Interface(
fn=process_inputs,
inputs=[
gr.Markdown(value="##### 🔔 You must grant access to the model repository before use."),
HuggingfaceHubSearch(
label="Hub Model ID",
placeholder="Search for model id on Huggingface",
search_type="model",
),
gr.Dropdown(
["q2_K", "q3_K", "q3_K_S", "q3_K_M", "q3_K_L", "q4_0", "q4_1", "q4_K", "q4_K_S", "q4_K_M", "q5_0", "q5_1", "q5_K", "q5_K_S", "q5_K_M", "q6_K", "q8_0", "f16"],
label="Quantization Option",
info="GGML quantisation options",
value="q4_0",
filterable=False
),
gr.Textbox(label="Email", placeholder="Enter your email here")
],
outputs = gr.Markdown(
label="output",
value="##### Please enter the model URL, select a quantization method, and provide your email address."
),
title="Create your own GGUF Quants, blazingly fast ⚡!",
allow_flagging="never"
)
theme = gr.themes.Base(text_size="lg")
with gr.Blocks(theme=theme) as demo:
gr.Markdown(value="### 🔔 You must be logged in to use this service.")
gr.LoginButton(min_width=250)
iface.render()
gr.Markdown(value="We sincerely thank our community members, [Perry](https://huggingface.co/PerryCheng614), [Brian](https://huggingface.co/JoyboyBrian), [Qi](https://huggingface.co/qiqiWav), for their extraordinary contributions to this GGUF converter project.")
demo.launch(share=True)
|