Join us at the the upcoming #GenAI Tools, Infra & Open-source Virtual Conference hosted by the team at @MLOpsWorld
. We'll show you how to break your dependency on #OpenAI by fine-tuning small open-source #LLMs! Save your spot – it's free to attend: https://
pbase.ai/3UDoTTI!
LLMS
-
Break OpenAI Dependency: Fine-tune Open-source LLMs at Virtual Conference
By
–
-
Homegrown Large Language Models: Building Local LLM Solutions
By
–
The Case of Homegrown Large Language Models: Recent developments in building large language models (LLMs) to boost generative AI in local languages have caught everyone’s attention. This post focuses on the needs and challenges of homegrown LLMs amid the… https://
kdnuggets.com/the-case-of-ho
megrown-large-language-models?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=the-case-of-homegrown-large-language-models
… -
Token usage now available for Chat Completions streaming
By
–
We just added token usage when streaming on Chat Completions. Thanks again for this suggestion, more to come!
-
Chat Completions API Usage Statistics Now Available
By
–
We just released usage stats on the Chat Completions API! Hope this helps!
-
Fine-tuning LLMs with Enterprise Data for Business Automation
By
–
While Llama 3 and Phi-3 are amazing breakthroughs, they must be trained on enterprise data before they can be trusted to automate critical business functions. AI data development is the key to fine-tuning LLMs for domain-specific tasks. https://
buff.ly/3UpUVST -
LLM Product Development: Beyond Initial Success Plateau
By
–
4. Initial success with LLMs can be misleading It took them 1 month to achieve 80% of the experience they wanted, and additional 4 months to surpass 95%. The initial success made them underestimate how challenging it is to improve the product, especially dealing with
-
Trading Throughput for Latency: LLM Performance Optimization
By
–
2. Sacrificing throughput for latency
Originally, they focused on TTFT (Time To First Token), but realized that TBT (Time Between Token) hurt them more, especially with Chain-of-Thought queries where users don’t see the intermediate outputs. They found that TTFT and TBT -
LinkedIn’s LLM deployment insights: YAML outputs and token optimization
By
–
Really enjoyed LinkedIn's report on what worked and what didn't when deploying LLM applications. 4 takeaways. 1. Structured outputs
They chose YAML over JSON as the output format because YAML uses less tokens. Initially, only 90% of the outputs are correctly formatted YAML. They -
ML NLP LLMs RAG Newsletter Daily Tips Tutorials
By
–
If you’re interested in:
– ML/NLP
– LLMs
– RAG My Newsletter → http://
unwindai.substack.com Everyday, I share tip & tutorials on above topics on X and my newsletter. -
Quantization in Depth: Compressing ML Models Efficiently
By
–
Have you used quantization with an open source machine learning library, and wondered how quantization works? How can you preserve model accuracy as you compress from 32 bits to 16, 8, or even 2 bits? In our new short course, Quantization in Depth, taught by @huggingface's… pic.twitter.com/7sj1Ivv5a4
— Andrew Ng (@AndrewYNg) 6 mai 2024Have you used quantization with an open source machine learning library, and wondered how quantization works? How can you preserve model accuracy as you compress from 32 bits to 16, 8, or even 2 bits? In our new short course, Quantization in Depth, taught by @huggingface
's