Revert to full N-ATLaS model - GGUF approaches failed
8bf3bf5
Fola-AI
commited on
Commit History
Fix llama-cpp-python loading - use hf_hub_download + Llama constructor
40af153
Fola-AI
commited on
Switch to llama-cpp-python for GGUF model - native quantized inference
3d5012a
Fola-AI
commited on
Fix GGUF loading - add gguf_file parameter
f0b9c25
Fola-AI
commited on
Fix syntax error in natlas_model.py
15734d8
Fola-AI
commited on
Simplify translations - GGUF model with GPU is fast enough
136baa0
Fola-AI
commited on
Switch to GGUF model for 3x smaller download and faster inference
ff6c790
Fola-AI
commited on
Optimize translation with batch processing - 5x faster
be16bc7
Fola-AI
commited on
Add compatibility stubs for HuggingFaceAPIClient
2695efb
Fola-AI
commited on
Use official N-ATLaS via transformers - no llama-cpp-python
068e72c
Fola-AI
commited on
Fix timeout - make llama-cpp-python optional
bcc0750
Fola-AI
commited on
Initial FarmEyes deployment - AI Powered Crop Disease Detection Program
f45df09
Fola-AI
commited on