Commit History

gallery fix
55dd4fe
Running

Zoro-chi commited on

gallery fix
6a2811f

Zoro-chi commited on

Configure Git LFS for binary files
50acde8

Zoro-chi commited on

gallery fix
2f33e0c

Zoro-chi commited on

cleaned code
647c8f0

Zoro-chi commited on

Fix prompt expansion to handle multiple variations and enforce length limit
c0b9c7a

Zoro-chi commited on

Fix prompt expansion with better text processing and robust fallbacks
cf7ae54

Zoro-chi commited on

prompt engineering
0ac957c

Zoro-chi commited on

Fix prompt expansion format and clean up code
b0d69de

Zoro-chi commited on

Limit prompt expansion to maximum 40 words with strict focus on original prompt
448eec3

Zoro-chi commited on

Limit prompt expansion to maximum of 100 words
87e965a

Zoro-chi commited on

Limit prompt expansion to exactly 3 sentences
0a9a6b2

Zoro-chi commited on

Completely revise GGUF loading to match direct ctransformers example
4547a45

Zoro-chi commited on

Fix GGUF model loading using correct configuration parameters format
b367fc7

Zoro-chi commited on

Fix GGUF model loading with proper config parameter structure
62f25ac

Zoro-chi commited on

Switch to TheBloke/TinyLlama-1.1B-Chat-GGUF for better prompt expansion with system prompts
94a2d06

Zoro-chi commited on

Implement reliable template-first approach for prompt expansion
2d1d207

Zoro-chi commited on

Implement structured creative prompt instructions for FLAN-T5-base model
dac04d5

Zoro-chi commited on

Switch to google/flan-t5-base and improve prompt expansion for better quality
b26638e

Zoro-chi commited on

Switch to distilgpt2 which is publicly available on Hugging Face
6c28b5c

Zoro-chi commited on

Switch to mistralai/MiniMistral-248M for better prompt enhancement
441d84a

Zoro-chi commited on

Enhance prompt expansion for FLAN-T5 model with specialized seq2seq handling
590186e

Zoro-chi commited on

Add support for google/flan-t5-small with proper sequence-to-sequence model handling
34d21a4

Zoro-chi commited on

phi 2 model
bbce178

Zoro-chi commited on

phi 1.5 model
d94a62b

Zoro-chi commited on

Disable quantization for Phi-1.5 model to avoid bitsandbytes dependency
69c28a3

Zoro-chi commited on

Switch to Microsoft Phi-1.5 model for better performance in Hugging Face Spaces
7235158

Zoro-chi commited on

Fix chat template error with DistilGPT2 by adding support for non-chat models
b83f7c0

Zoro-chi commited on

Disable model quantization in Hugging Face Spaces to avoid bitsandbytes dependency
0d08fec

Zoro-chi commited on

Set model environment variables directly in app.py for Hugging Face Spaces
40a0639

Zoro-chi commited on

llm changes
4e32dd5

Zoro-chi commited on

Fix model compatibility issues in Hugging Face Spaces
e317ed2

Zoro-chi commited on

Switch to TinyLlama GGUF model for much faster inference in Hugging Face Spaces
37ed2a0

Zoro-chi commited on

Fix LLM usage in Hugging Face Spaces with smaller model and import handling
f1cc7f4

Zoro-chi commited on

Fix pipeline initialization error and improve LLM handling for Hugging Face Spaces
a018b91

Zoro-chi commited on

deploy changes
2547144

Zoro-chi commited on

Fix Hugging Face Spaces issues: LLM URL error and app ID connection problems
e366aec

Zoro-chi commited on

Fix module import error for Hugging Face Spaces
e5ad63f

Zoro-chi commited on

updated README
bd22e77

Zoro-chi commited on

Add proper YAML metadata to README for Hugging Face Spaces
1921de3

Zoro-chi commited on

Initial commit
1d21f23

Zoro-chi commited on

initial commit
2ec20fe
unverified

Zoro-chi commited on