Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
Currently in the last commit: 2e57e764c0bf2c595ff1259f477f0156a5f75890
Executing this script to load a model in a linux system:
TOKENIZERS_PARALLELISM=true python generate.py \
--base_model=Qwen/Qwen2-7B-Instruct --prompt_type=qwen --use_gpu_id=True --gpu_id=-1 --max_seq_len=8192 \
--user_path=/opt/myDocuments/arsys.es/html/ --langchain_mode='UserData' --max_quality=True \
--add_chat_history_to_context=True --keep_sources_in_context=True --enable_ocr=True --enable_doctr=True \
--answer_with_sources=True --show_link_in_sources=True --append_sources_to_chat=True \
--hf_embedding_model="hkunlp/instructor-xl" \
--memory_restriction_level=0 --score_model=None --verbose=True \
--show_examples=True --compile_model=True \
--src_lang='Spanish' --tgt_lang='Spanish' \
--debug=True \
--pre_prompt_query='Always answer as helpfully as possible and follow ALL given instructions. Do not speculate or make up any kind of information. As long as you can, give responses in spanish language.' \
--share=True
Currently in the last commit: 2e57e764c0bf2c595ff1259f477f0156a5f75890 Executing this script to load a model in a linux system: