Add gguf_file parameter to tokenizer loading and introduce diagnostic script for GGUF validation

Fix GGUF filename in environment variable and update comment in requirements

Add protobuf requirement for GGUF model loading

Refactor application to implement GGUF backend with native transformers support; update requirements and add GGUF-specific entry point

Refactor model loading to utilize accelerate for device management; add test script to verify loading fix and prevent device conflicts

Refactor application to use lightweight backend; update requirements and add memory analysis script for optimized model configuration

Update Dockerfile and application entry point for GGUF backend; optimize memory usage in model parameters and requirements

d

Refactor backend service to support Gemma 3n model and update requirements; remove obsolete test script and add new dependency tests

c

b

l

a

Add metadata section to README for project details

aa

Add scripts for converting and generating UltraChat-style SFT dataset

update

Update Dockerfile: Add missing system dependencies for build

rabbit-ed

Cleanup: Remove unnecessary files and update .gitignore

update

chg model

change to adapter

try

upd

update to use unsloth + mistral

change model

try #1

upd

update

Fix model dependencies and warnings

Update model to unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Revert model back to gemma-3n-E4B-it-GGUF

Fix: Update to valid HuggingFace model and fix deprecation warnings

upd

fix

fix

update

upd

update

fix

Ignore Hugging Face cache directory

fix

Add API response endpoint and tests

Set gemma-3n-E4B-it-GGUF as main model for all text generation endpoints

Update app.py

🔧 Fix HuggingFace Space compatibility

🚀 Add multimodal AI capabilities with image-text-to-text pipeline

Update space

initial commit