Gemma 2 9B looks like a strong model for creative writing, especially with length correction. Here's a sample from EQ-Bench with the prompt, result, and analysis from Claude 3.5 Sonnet.
LLMS
-
Smaug-32K Release: Extended Context and Improved Reasoning
By
–
A couple of weeks ago, we released Smaug-32K, which extends beyond base Llama’s 8k context and improves on areas of hard reasoning and complex problems. Multiple of our enterprise customers currently have this in production, and it also has a full-green heatmap and great
-
Otio AI tool provides automated summaries for YouTube videos
By
–
5- Résumer les vidéos YouTube Otio propose de brefs résumés de vos vidéos YouTube, fournissant des informations clés pour augmenter votre productivité !
-
AI-powered automated content summarization tool
By
–
3- Collectez tout ce que vous voulez et résumez-le automatiquement, prêt à être discuté. Résumez différents types de contenus tels que des documents, des PDF, des vidéos YouTube, des fichiers audio, des tweets, des fichiers CSV et des articles sans effort.
-
Google Gemma 2, OpenAI partnerships, and new AI tools
By
–
Top stories in AI today: -Google launches Gemma 2, Gemini upgrades
-TIME strikes major deal with OpenAI
-Use ChatGPT to turn docs into spreadsheets
-OpenAI’s critics train smarter AI systems
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/googles-ai-d
ouble-feature
… -
Using New Gemma 2 Models with AutoTrain
By
–
In case, I didnt mention, you can use both new Gemma 2 models with AutoTrain
-
GPT-4o limitations in end-to-end video processing workflow
By
–
GPT4o isn’t an end-to-end model now? they need to extract frames from a video generated by Sora and then process them with Vision? What a seamless workflow https://t.co/9PbqlD23vF
— CHOI (@arrakis_ai) 28 juin 2024GPT4o isn’t an end-to-end model now? they need to extract frames from a video generated by Sora and then process them with Vision? What a seamless workflow
-
MIT Develops LLM-Guided Robot Navigation for Complex Tasks
By
–
@MIT researchers have recently developed a method using language inputs to guide robots in complex navigation tasks. By leveraging large language models (LLMs), they enable robots to navigate through material handling, disaster relief, and rescue operations. This approach uses
-
Claude API Usage Confirms Actual Claude Implementation
By
–
No, as it's using the claude API itself. So, technically this is actual claude.