There's a new king of open-source. The new LLM from @databricks just beat Mixtral! – 132B total params (16 experts), 36B active (4 experts)
– Trained on *12T* tokens
– 32K context length From my initial tests, I'm really impressed.
LLMS
-
Databricks New LLM Beats Mixtral in Open-Source Race
By
–
-
Hugging Face discusses purpose-trained AI models for B2B sector
By
–
#hf #friends #solarllm We had a great dinner with Hugging Face friends @art_zucker in Korea. We discussed AI challenges. In the B2B sector, smaller, purpose-trained models seem to perform better. Overall, it was a heartwarming conversation about the future of Upstage. It was a
-
Off-by-One Error in Autoregressive Model Training
By
–
hahah I’ve made this mistake too; it’s pretty easy to do in autoregressive model-training. just an off-by-one error: predict token T from token T instead of T+1
-
Blogs on Large Language Models from Diverse Authors
By
–
4/ Blogs on LLMs from wide range of authors
-
Building Generative AI Applications with LangChain and OpenAI
By
–
3/ Building generative AI applications using LangChain and OpenAI APIs
-
OpenAI Function Calling and Assistants API Explained
By
–
2/ Everything you need to know about OpenAI function calling and assistants API
-
Best Large Language Models Blogs and Applications Guide
By
–
Check out the best large language models blogs and applications available out there
-
Mastering NL2SQL with Langchain: End-to-End Application
By
–
1/ Mastering NL2SQL with Langchain Build end to end NL2SQL application using langchain
-
Beyond Benchmarks: Evaluating AI Models on Business Priorities
By
–
Benchmarks now match this anecdotal performance. There’s a place for formal benchmarks. But that’s not the only thing businesses look at when picking models. It’s: performance ON SPECIFIC TASK (ex: may need huge context), cost, partnerships, PRIVACY and security, speed, etc.
-
Build Enterprise AI Systems at Scale with Generative AI
By
–
Use #GenerativeAI from @AbacusAI to Build End-to-End Enterprise Applied #AI Systems at scale: https://t.co/m6xtTyEAdK = the world's first end-to-end #MLOps and #LLMOps platform where AI builds Applied AI agents and systems!
— Kirk Borne (@KirkDBorne) 27 mars 2024
——#MachineLearning #ML #DataScience #EnterpriseAI #LLMs pic.twitter.com/LwvNtDEx0FUse #GenerativeAI from @AbacusAI to Build End-to-End Enterprise Applied #AI Systems at scale: https://
abacus.ai = the world's first end-to-end #MLOps and #LLMOps platform where AI builds Applied AI agents and systems!
——
#MachineLearning #ML #DataScience #EnterpriseAI #LLMs