Here's info on the estimated emissions for pre-training for the Gemma 2 family of models (from a paper published in July 2024). Those models are open-sourced, so should be easy for external parties to measure inference costs under various compute environments/settings (as
OPEN SOURCE
-
Checkr Optimizes Hiring with Fine-Tuned Open Source Small Models
By
–
@checkr , Inc. is changing the way companies hire with #AI-driven automation and their doing it with small models (#SLMs)! Check out our latest case study to hear how Vlad Bukhin and the Checkr team fine-tuned small #opensource models that are more accurate, 30x #faster
-
LLM360 releases TxT360: 15T token pre-training dataset
By
–
TxT360: new pre-training dataset with 15T tokens Impressive release from LLM360 with a new pre-training dataset of 15T tokens. It includes a lot of new sources compared to previous open-sourced pre-training datasets, like FreeLaw, PG-19 (books), etc. It's really interesting
-
LangGraph Launches Long-Term Memory Support for AI Agents
By
–
We put a lot of efforts into some great resources around this launch! Memory is a under explored and very open ended topic… more than anything, we wanted to share how we are thinking about it and get feedback Blog post: https://
blog.langchain.dev/launching-long
-term-memory-support-in-langgraph/
…
Conceptual docs: -
Community Papers on Hugging Face Hub Daily
By
–
some days im not active but the community is still posting papers to https://
huggingface.co/papers I check it daily in the morning to find the latest papers and has a discussion section to talk directly with the authors -
Debiasing Large Language Models with Synthetic Data Pipeline
By
–
We are excited to share our latest work on debiasing large language models, accepted to COLM 2024 We introduce a lightweight, simple pipeline using ChatGPT to generate synthetic data for debiasing open-source LLMs through parameter-efficient fine-tuning. Our method outperforms
-
Faster Whisper Gradio: Real-time Speech-to-Text Application
By
–
Faster Whisper Gradio Real-time speech-to-text application using Faster Whisper with Gradio. This application utilizes DeeplX for translation.
-
openai-gradio: Simplified Web Apps with OpenAI API
By
–
openai-gradio a Python package that makes it very easy for developers to create web apps that are powered by @OpenAI API in a few lines of code pip install openai-gradio
-
Llama 3.2 achieves 10x improvement over previous generation
By
–
the new 1 billion parameters Llama model (version 3.2) is head-to-head with the 13 times larger version of one years ago (llama 13B version 2) on lmsys chatbot arena exciting to see such 10x improvements on challenging benchmark it's an amazing sign for small/local/open models
-
Build Your Own OpenAI Assistant with Open Source Tools
By
–
What if you could create your own OpenAI Assistant with Realtime API that can:
— FlowiseAI (@FlowiseAI) 7 octobre 2024
🌐 Browse the Web
📚 Search Files (RAG)
💻 Run Code Interpreter
All using open source tools.
Check it out pic.twitter.com/7Mm6YxJWflWhat if you could create your own OpenAI Assistant with Realtime API that can: Browse the Web Search Files (RAG) Run Code Interpreter All using open source tools. Check it out