OLMo: Accelerating the Science of Language Models Groeneveld et al.: https://
arxiv.org/abs/2402.00838 #ArtificialIntelligence #DeepLearning #MachineLearning
RESEARCH
-
OLMo: Accelerating the Science of Language Models
By
–
-
LoRAX v0.7 Release: Runtime LoRA Merging Per Request
By
–
Announcing the Release of #LoRAX v0.7: Merge #LoRAs at runtime per request! Use cases: Mix LoRAs to improve response (Mixture of LoRAs) No need to pick the right #LoRA by hand Combine with a ranker and merge top-k LoRAs https://
pbase.ai/42tbst0 -
LLM Hallucinations in Legal Contexts: Study Reveals Significant Risks
By
–
Hallucinations are a big problem with large language models. How pervasive is it in legal contexts? A study involving three popular LLMs raises red flags.
-
Measuring Economic Value Beyond Monetary Spending
By
–
Is there a good way to compare national
economies that does not rely on money spent but value created? -
NAIRR: National AI Research Resource Materialized from 2021 Vision
By
–
This video aged well: Published in 2021, here we explained why we were calling for the creation of a national research cloud—now materialized as the National AI Research Resource or NAIRR. https://
bit.ly/3SFaCGc -
Research@ Bangalore Inspires AI Community with Lightning Talks
By
–
We’re inspired by the incredible lightning talks and demos shared at Research@ Bangalore. A special shoutout to all of our speakers and attendees from the researcher, developer, and academic communities and beyond. Together, we're shaping the future and driving meaningful change.
-
Chain-of-Thought Information Density and Compute Scaling
By
–
A key insight from chain-of-thought is around the idea of information density. Language models can only do so much with a single forward pass, and so the amount of compute the language model can use must be scaled proportional to how hard a prompt is to solve. What is
-
Academic Integrity and Disciplinary Compromise in Research
By
–
In my interactions about the topic, I found that most academics believe in the integrity of most other academics, which can lead to weird effects when the mainstream of a discipline gets compromised
-
Fine-tuning Phi-2 with OpenHermes-2.5 Dataset
By
–
My goal next is to fine-tune phi-2 using the incredible OpenHermes-2.5 dataset from @teknium
. Stay tuned! -
TimesFM: Zero-Shot Time Series Forecasting Model by Google
By
–
TimesFM is a forecasting model, pre-trained on a large time-series corpus of 100 billion real world time-points, that displays impressive zero-shot performance on a variety of public benchmarks from different domains and granularities. Learn more → https://
goo.gle/480VRlm