h2ogpt: Another Open-source large language model by H2O.ai team

Another full open source large language model from H2Oa.o AI team with 12B and 20B parameters, trained on the Pile open-source dataset is released with the following features:

• Open-source repository with fully permissive, commercially usable code, data and models
• Code for preparing large open-source datasets as instruction datasets for fine-tuning of large language models (LLMs), including prompt engineering
• Code for fine-tuning large language models (currently up to 20B parameters) on commodity hardware and enterprise GPU servers (single or multi node)
• Code for enabling LoRA (low-rank approximation) and 8-bit quantization for memory-efficient fine-tuning and generation.
• Code to run a chatbot on a GPU server, with shareable end-point with Python client API
• Code to evaluate and compare the performance of fine-tuned LLMs

== Video Timeline == (00:00) Content Intro (00:15) Introducing H2O (01:30)H2O.ai Intro (03:05) h2ogpt (04:55) h2ogpt Chatbot (09:35) h2ogpt Details (10:40) H2O llmstudio Intro (13:20) Conclusion

=== Resources ===

• https://h2o.ai/
• https://h2o.ai/events/h2o-world/
• https://github.com/h2oai/h2ogpt
• https://github.com/h2oai/h2o-llmstudio
• https://huggingface.co/spaces/h2oai/h2ogpt-chatbot2
• https://huggingface.co/spaces/h2oai/h2ogpt-chatbot
• https://www.kaggle.com/code/philippsinger/openassistant-conversations-dataset-oasst1

Please visit: https://prodramp.com | @prodramp https://www.linkedin.com/company/prodramp

Content Creator: Avkash Chauhan (@avkashchauhan) https://www.linkedin.com/in/avkashchauhan

Tags: #stablelm #stableai #finetunellm #openai #python #ai #langchain #chromadb ... https://www.youtube.com/watch?v=aFU3VRGE2gk