Spaces:
Sleeping
Sleeping
File size: 10,782 Bytes
4f42f3b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 |
import gradio as gr
from huggingface_hub import InferenceClient
import json
from datetime import datetime, timedelta
import os
# List of 20 well-known large language models
MODELS = [
"meta-llama/Llama-3.3-70B-Instruct",
"meta-llama/Llama-3.1-405B-Instruct",
"mistralai/Mixtral-8x7B-Instruct-v0.1",
"mistralai/Mistral-7B-Instruct-v0.3",
"google/gemma-2-27b-it",
"google/gemma-2-9b-it",
"Qwen/Qwen2.5-72B-Instruct",
"Qwen/Qwen2.5-Coder-32B-Instruct",
"microsoft/Phi-3.5-mini-instruct",
"tiiuae/falcon-180B-chat",
"HuggingFaceH4/zephyr-7b-beta",
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"01-ai/Yi-34B-Chat",
"databricks/dbrx-instruct",
"openchat/openchat-3.5-0106",
"teknium/OpenHermes-2.5-Mistral-7B",
"cognitivecomputations/dolphin-2.6-mixtral-8x7b",
"Nexusflow/Starling-LM-7B-beta",
"EleutherAI/llemma_34b",
"upstage/SOLAR-10.7B-Instruct-v1.0"
]
def get_usage_data(request: gr.Request):
"""Get usage data from browser storage"""
try:
# This will be handled by JavaScript
return {"chats_used": 0, "reset_time": None}
except:
return {"chats_used": 0, "reset_time": None}
def check_usage_limit(chats_used, reset_time):
"""Check if user has exceeded usage limit"""
if reset_time:
reset_dt = datetime.fromisoformat(reset_time)
if datetime.now() > reset_dt:
return 0, None # Reset the counter
return chats_used, reset_time
def chat_with_model(message, history, model_name, hf_token, chats_used, reset_time):
"""Chat with the selected model"""
# Check usage limit
current_chats, current_reset = check_usage_limit(chats_used, reset_time)
if current_chats >= 2:
if current_reset:
reset_dt = datetime.fromisoformat(current_reset)
return history, current_chats, current_reset, f"β οΈ You've used your 2 free chats this month. Next reset: {reset_dt.strftime('%Y-%m-%d %H:%M')}"
return history, current_chats, current_reset, "β οΈ You've used your 2 free chats this month."
if not hf_token:
return history, current_chats, current_reset, "β οΈ Please log in with your Hugging Face token first."
if not message.strip():
return history, current_chats, current_reset, ""
try:
# Initialize client with user's token
client = InferenceClient(token=hf_token)
# Prepare messages for API
messages = []
for user_msg, assistant_msg in history:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": message})
# Stream response
response_text = ""
history.append([message, ""])
for chunk in client.chat_completion(
model=model_name,
messages=messages,
max_tokens=2000,
stream=True,
):
if chunk.choices[0].delta.content:
response_text += chunk.choices[0].delta.content
history[-1][1] = response_text
yield history, current_chats, current_reset, ""
# Increment usage counter
new_chats_used = current_chats + 1
new_reset_time = current_reset
if new_reset_time is None:
# Set reset time to 1 month from now
new_reset_time = (datetime.now() + timedelta(days=30)).isoformat()
status_msg = f"β
Chat successful! Chats used: {new_chats_used}/2"
if new_chats_used >= 2:
reset_dt = datetime.fromisoformat(new_reset_time)
status_msg += f" | Next reset: {reset_dt.strftime('%Y-%m-%d %H:%M')}"
yield history, new_chats_used, new_reset_time, status_msg
except Exception as e:
error_msg = f"β Error: {str(e)}"
if "429" in str(e):
error_msg = "β Rate limit exceeded. Please try again later."
elif "401" in str(e) or "403" in str(e):
error_msg = "β Invalid Hugging Face token. Please check your token."
yield history, current_chats, current_reset, error_msg
# Custom CSS
css = """
#header {
text-align: center;
padding: 20px;
background: linear-gradient(90deg, #667eea 0%, #764ba2 100%);
color: white;
border-radius: 10px;
margin-bottom: 20px;
}
#header a {
color: #FFD700;
text-decoration: none;
font-weight: bold;
font-size: 0.9em;
}
#header a:hover {
text-decoration: underline;
}
#chatbot {
height: 500px;
}
.usage-info {
padding: 10px;
border-radius: 5px;
margin: 10px 0;
}
"""
# JavaScript for localStorage management
js_code = """
function() {
// Load usage data from localStorage
const usageData = localStorage.getItem('hf_chat_usage');
let chatsUsed = 0;
let resetTime = null;
if (usageData) {
const data = JSON.parse(usageData);
chatsUsed = data.chats_used || 0;
resetTime = data.reset_time || null;
// Check if reset time has passed
if (resetTime && new Date() > new Date(resetTime)) {
chatsUsed = 0;
resetTime = null;
localStorage.setItem('hf_chat_usage', JSON.stringify({chats_used: 0, reset_time: null}));
}
}
return [chatsUsed, resetTime];
}
"""
# Build the Gradio interface
with gr.Blocks(css=css, theme=gr.themes.Soft(), title="HF Model Chat - 2 Free Chats/Month") as demo:
# Header with attribution
gr.HTML("""
<div id="header">
<h1>π€ Hugging Face Model Chatbot</h1>
<p>Chat with 20+ Large Language Models | 2 Free Chats per Month</p>
<p><a href="https://huggingface.co/spaces/akhaliq/anycoder" target="_blank">Built with anycoder</a></p>
</div>
""")
# State variables
chats_used_state = gr.State(0)
reset_time_state = gr.State(None)
with gr.Row():
with gr.Column(scale=1):
gr.Markdown("### π Login & Settings")
hf_token = gr.Textbox(
label="Hugging Face Token",
placeholder="hf_...",
type="password",
info="Enter your HF token to use the models"
)
gr.Markdown("""
<small>Get your token from
<a href="https://huggingface.co/settings/tokens" target="_blank">
Hugging Face Settings</a></small>
""")
model_dropdown = gr.Dropdown(
choices=MODELS,
value=MODELS[0],
label="Select Model",
info="Choose from 20 large language models"
)
usage_display = gr.Markdown("### π Usage: 0/2 chats used")
status_box = gr.Textbox(
label="Status",
interactive=False,
visible=True
)
with gr.Column(scale=2):
gr.Markdown("### π¬ Chat")
chatbot = gr.Chatbot(
elem_id="chatbot",
type="messages",
height=500,
show_copy_button=True
)
with gr.Row():
msg_input = gr.Textbox(
placeholder="Type your message here...",
show_label=False,
scale=4
)
send_btn = gr.Button("Send", variant="primary", scale=1)
clear_btn = gr.Button("Clear Chat")
# Usage info display
def update_usage_display(chats_used, reset_time):
msg = f"### π Usage: {chats_used}/2 chats used"
if chats_used >= 2 and reset_time:
reset_dt = datetime.fromisoformat(reset_time)
msg += f"\n**Next reset:** {reset_dt.strftime('%Y-%m-%d %H:%M')}"
return msg
# Event handlers
def user_submit(message, history, model, token, chats_used, reset_time):
return "", history, chats_used, reset_time, ""
submit_event = msg_input.submit(
user_submit,
[msg_input, chatbot, model_dropdown, hf_token, chats_used_state, reset_time_state],
[msg_input, chatbot, chats_used_state, reset_time_state, status_box],
queue=False
).then(
chat_with_model,
[msg_input, chatbot, model_dropdown, hf_token, chats_used_state, reset_time_state],
[chatbot, chats_used_state, reset_time_state, status_box]
)
send_btn.click(
user_submit,
[msg_input, chatbot, model_dropdown, hf_token, chats_used_state, reset_time_state],
[msg_input, chatbot, chats_used_state, reset_time_state, status_box],
queue=False
).then(
chat_with_model,
[msg_input, chatbot, model_dropdown, hf_token, chats_used_state, reset_time_state],
[chatbot, chats_used_state, reset_time_state, status_box]
)
clear_btn.click(
lambda: ([], ""),
None,
[chatbot, status_box],
queue=False
)
# Update usage display when state changes
chats_used_state.change(
update_usage_display,
[chats_used_state, reset_time_state],
usage_display
)
# Save to localStorage on state change
demo.load(
None,
None,
[chats_used_state, reset_time_state],
js="""
function() {
const usageData = localStorage.getItem('hf_chat_usage');
let chatsUsed = 0;
let resetTime = null;
if (usageData) {
const data = JSON.parse(usageData);
chatsUsed = data.chats_used || 0;
resetTime = data.reset_time || null;
if (resetTime && new Date() > new Date(resetTime)) {
chatsUsed = 0;
resetTime = null;
localStorage.setItem('hf_chat_usage', JSON.stringify({chats_used: 0, reset_time: null}));
}
}
return [chatsUsed, resetTime];
}
"""
)
# Save changes to localStorage
chats_used_state.change(
None,
[chats_used_state, reset_time_state],
None,
js="""
function(chats, reset) {
localStorage.setItem('hf_chat_usage', JSON.stringify({
chats_used: chats,
reset_time: reset
}));
}
"""
)
if __name__ == "__main__":
demo.launch() |