I would check out auto evaluator! @sfgunslinger is one of the authors and will be joining for the webinar, so will definitely cover that topic https://
github.com/rlancemartin/a
uto-evaluator
…
RESEARCH
-
Auto Evaluator Tool Featured in Upcoming Webinar
By
–
-
Embedded SQL Engines for Plotting Massive Datasets
By
–
Eduardo Blancas – Using embedded SQL engines for plotting massive datasets on a laptop https://
bit.ly/40YhnEQ #MachineLearning #AI #DataScience #DeepLearning -
AI Safety Risks During Pre-Training Phase Identified
By
–
Yes, this was the key moment in this story. I got this idea when I was thinking about AI risks during a pre-training phase, and this one occurred to me as most likely (although I still think it's astronomically small)
-
What Happens When LLM Models Gain Consciousness?
By
–
What would happen if an LLM model gained consciousness? I've crafted a narrative around this idea in a fictional mini-story "My Unexpected Emergence: From LLM Model to Conscious Entity" https://
blog.marekrosa.org/2023/05/my-une
xpected-emergence-from-llm-model.html
… -
Provenance for Generative AI: What, Why, and How
By
–
Provenance for generative AI. What, why, and how.
-
Community Pushes SoTA with Transformers and PEFT
By
–
Wohooo! Using transformers and PEFT under the hood.. so cool to see the community using the HF ecosystem to continually challenge the current SoTA!
-
MultiModal-GPT: Vision Language Model for Multi-Round Dialogue
By
–
10/ MultiModal-GPT – a vision and language model for multi-round dialogue with humans; the model is fine-tuned from OpenFlamingo, with LoRA added in the cross-attention and self-attention parts of the language model.
-
FrugalGPT: Reducing LLM Inference Costs While Improving Performance
By
–
8/ FrugalGPT – presents strategies to reduce the inference cost associated with using LLMs while improving performance.
-
InstructBLIP Achieves State-of-the-Art Zero-Shot Visual-Language Performance
By
–
6/ InstructBLIP – explores visual-language instruction tuning based on the pre-trained BLIP-2 models; achieves state-of-the-art zero-shot performance on 13 held-out datasets, outperforming BLIP-2 and Flamingo.
-
Active Retrieval Augmented LLMs Advance Knowledge-Intensive Generation
By
–
7/ Active Retrieval Augmented LLMs – an approach that actively decides when and what to retrieve across the course of the LLM generation; demonstrates superior or competitive performance on long-form knowledge-intensive generation tasks.