The problem with LLMs is what it's always been with NLP: if people can't tell what they're good for and not, they'll wind up not using them for much.
LLMS
-
Recent LangChain Updates and New Features
By
–
A lot of stuff has been added to LangChain recently For a good thread on how we're thinking about it, see the below And of course, check out all the additions at https://
github.com/hwchase17/lang
chain/
… -
GenSLMs trained on full sequence length in under one day
By
–
"To enable training of the larger models on the full sequence length (10,240 tokens), we leveraged… CS-2… and obtained GenSLMs that converge in less than a day.” ACM article on our award for this research: https://
hubs.li/Q01s-1f40 Full article: https://
hubs.li/Q01s-0Yy0 -
Generative AI Models and Search Engine Citations
By
–
Generation Engines w/ Search Engine Citations?
-
AI System Malfunction Responds Only With 42
By
–
anyway its gonna be awhile, seems broken, just says "42" to every prompt?!
-
Six Most Impactful Language Models in History
By
–
Six of the most impactful language models in history: 1. BERT
2. BART
3. T5
4. GPT-3
5. LaMDA
6. Switch Transformers v/
@Saboo_Shubham_ -
LangChain 0.0.19: Sequential Chains and Vector DB Updates
By
–
LangChain version 0.0.19 Sequential chains: define a list of sub-chains and run them in order
Expose prompt for changing in vector db/qa
Clean up some documentation -
RL with KL Penalties Reframed as Bayesian Inference
By
–
RL with KL penalties is better viewed as Bayesian inference Korbak et al.: https://
arxiv.org/abs/2205.11275 #ArtificialIntelligence #DeepLearning #MachineLearning -
Explaining Model Parameters in Machine Learning
By
–
for those of you wondering, what is a parameter? It’s a configuration variable that is internal to the model and whose value can be estimated from the given data. They are required by the model when making predictions. The values define the skill of the model on your problem.
-
PyTorch Optimum Achieves 4.5x Speedup for Transformer Models
By
–
A collaboration with @PyTorch to make transformer-based models faster using optimum library! Up to 4.5x speedup for text, vision and audio models using a one liner! Try it out now: https://
huggingface.co/docs/optimum/b
ettertransformer/overview
…