simple-chat / app.py

Commit History

docs: Update README with multi-environment support and remove redundant footer
f1ac66c

alex4cip Claude commited on

fix: Import spaces before torch to prevent CUDA initialization error
09e4bc2

alex4cip Claude commited on

feat: Center-align submit button with input field
27061cd

alex4cip Claude commited on

feat: Enable RTX 5080 GPU support with PyTorch nightly (CUDA 12.8)
6612ab5

alex4cip Claude commited on

feat: Add RTX 5080 support and remove requirements-local.txt
2c96300

alex4cip Claude commited on

feat: Add comprehensive hardware environment detection system
a0f4ab8

alex4cip Claude commited on

feat: Add dynamic model count display
fc890b6

alex4cip Claude commited on

feat: Bind Gradio server to 0.0.0.0 for external access
751b361

alex4cip Claude commited on

feat: Add 3 Korean LLM models and update dependencies
bfd0656

alex4cip Claude commited on

feat: Add thinking indicator during bot response generation
0155077

alex4cip Claude commited on

feat: Show user message immediately before bot response
c3dd276

alex4cip Claude commited on

fix: Add user message to history in messages format
d64290b

alex4cip Claude commited on

fix: Migrate to OpenAI-style messages format
2384d41

alex4cip Claude commited on

fix: Add attention_mask to improve generation reliability
7cf114c

alex4cip Claude commited on

feat: Add flexible hardware support (ZeroGPU + CPU Upgrade)
b44b68c

alex4cip Claude commited on

fix: Change truncate to truncation in tokenizer.encode()
aa3c1df

alex4cip Claude commited on

fix: Import spaces before CUDA-related packages
ab64ed7

alex4cip Claude commited on

feat: Add ZeroGPU support for Llama-2-Ko 7B
9171967

alex4cip Claude commited on

Revert "test: Add Llama-2-Ko 7B model for large model testing"
a93accb

alex4cip commited on

test: Add Llama-2-Ko 7B model for large model testing
5d8fc93

alex4cip Claude commited on

feat: Add single model (DialoGPT-small) for incremental testing
718425d

alex4cip Claude commited on

test: Deploy minimal echo version to debug 500 errors
c7bf517

alex4cip commited on

fix: Revert to torch_dtype for compatibility with all models
476edda

alex4cip Claude commited on

fix: Remove model preloading and fix dtype deprecation warning
ecce181

alex4cip Claude commited on

fix: Add explicit queue=False to all event handlers
f2581b9

alex4cip Claude commited on

refactor: Replace ChatInterface with pure Blocks to fix HTTP/2 errors
83d2348

alex4cip Claude commited on

fix: Remove concurrency_limit parameter causing 500 errors
e6282fc

alex4cip Claude commited on

fix: Remove deprecated enable_queue parameter for Gradio 5.x
a82c24c

alex4cip Claude commited on

fix: Disable queue system to resolve HTTP/2 SSE errors
3228df9

alex4cip Claude commited on

fix: Replace examples with interactive buttons for model switching
42fba8e

alex4cip Claude commited on

feat: Improve input field visibility with custom styling
7dd37b0

alex4cip Claude commited on

feat: Add autofocus to message input field
e57b6dc

alex4cip Claude commited on

fix: Add fallback for model loading with better error handling
884298e

alex4cip Claude commited on

fix: Add safetensors support and improve model loading
e6dc16b

alex4cip Claude commited on

feat: Add better Korean language models
c6d4144

alex4cip Claude commited on

fix: Use chatbot_state instead of chatbot_value
fb55a82

alex4cip Claude commited on

feat: Optimize for Hugging Face Spaces deployment
5c29192

alex4cip Claude commited on

fix: Clear chat history when changing LLM models
c7ca2c5

alex4cip Claude commited on

feat: Hugging Face LLM chatbot with multi-language support
c9ef1fe

alex4cip Claude commited on