We've consistently heard that the biggest blocker for enterprises to deploy "ChatGPT-your-data" applications is hallucinations Come learn from @sfgunslinger @nickscamara_ and @deepset_ai how to (1) limit hallucinations and (2) evaluate your app to make sure there aren't any!
GENERATIVE AI
-
Provenance for Generative AI: What, Why, and How
By
–
Provenance for generative AI. What, why, and how.
-
Human and AI Collaboration: Technology as an Enabler
By
–
Turn Technology into an Enabler with Human + #AI Collaboration: https://
linkedin.com/pulse/turning-
technology-enabler-human-ai-collaboration-vin-vashishta
… article by @v_vashishta = #SAPSapphire = Look inside and be inspired by @SAP
's latest #GenerativeAI developments: https://
sap.com/programs/be-re
ady-ai.html?campaigncode=CRM-YA23-INT-2021326&source=socialad-na-influencer-twitter
… -
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.
-
StarCoder: Open-Source 15.5B Parameter Code Language Model
By
–
9/ StarCoder – an open-access 15.5B parameter LLM with 8K context length and is trained on large amounts of code spanning 80+ programming languages.
-
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.
-
TidyBot: Robot Learning User Preferences with LLM Planning
By
–
4/ TidyBot – shows that robots can combine language-based planning and perception with the few-shot summarization capabilities of LLMs to infer generalized user preferences that are applicable to future interactions.https://t.co/2Hv9FZh4Rx
— DAIR.AI (@dair_ai) 14 mai 20234/ TidyBot – shows that robots can combine language-based planning and perception with the few-shot summarization capabilities of LLMs to infer generalized user preferences that are applicable to future interactions.