OLMo: Accelerating the Science of Language Models Groeneveld et al.: https://
arxiv.org/abs/2402.00838 #ArtificialIntelligence #DeepLearning #MachineLearning
GENERATIVE AI
-
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.
-
Google Bard Image Generation Unavailable in UK Market
By
–
Unfortunately it's not available in UK yet per https://
support.google.com/bard/answer/13
594961?visit_id=638425078772178503-3179143020&p=exup_lm_imagen&rd=1#generated_images
… -
Generated Cat Image as Visual Representation of Catness Concept
By
–
The generated appearance of a cat is a brush to visually represent the idea of catness
-
Generative AI as Tool: Prompt Control Versus Randomness
By
–
Current generative AI is not an artist, it’s a highly powerful brush, distilled from all other brushes it has been trained on. Its content is not the pretty picture, but the prompt and a random number, and it’s limited by the ratio of achievable prompt control to randomness.
-
Microsoft Copilot Studio: New Conversational and Generative AI Capabilities
By
–
Announcing Microsoft Copilot Studio | Microsoft 365 Blog bit.ly/49fUTCZ Copilot Studio is included in Copilot for Microsoft 365 and brings together a set of powerful conversational capabilities—from custom GPTs, to generative AI plugins, to manual topics [Translated from EN to English]
→ View original post on X — @marktabnet, 2024-02-02 21:10 UTC
-
Angry Email Translator GPT turns rage into polite emails
By
–
Imagine losing a job over an angry email.
— God of Prompt (@godofprompt) 2 février 2024
That's why I created Angry Email Translator GPT 😡
It instantly turns angry text into a polite and thoughtful email, maintaining its core message.
👉 Try it out here: https://t.co/90Ok81YAs8#CustomGPT #OpenAI #GodofPrompt pic.twitter.com/FfT98KS12zImagine losing a job over an angry email. That's why I created Angry Email Translator GPT It instantly turns angry text into a polite and thoughtful email, maintaining its core message. Try it out here: https://
godofprompt.ai/gpts/angry-ema
il-translator
… #CustomGPT #OpenAI #GodofPrompt -
Cerebras Systems Recognized in Newsweek Excellence Index 2024
By
–
Cerebras Systems has been recognized in the @Newsweek Excellence Index 2024! As thought leaders in Generative AI, we're honored to stand among companies exemplifying success and responsibility across various industries. This recognition reflects our commitment to
-
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!