NeuralDaredevil-8B Daredevil-8B has the highest MMLU score among 8B models on the Open LLM Leaderboard. Thanks to abliteration and DPO fine-tuning, I managed to create an uncensored version that outperforms Llama 3 Instruct 8B on every benchmark (9 tested).
RESEARCH
-
Codestral Model Benchmarks and Compression Trends Analysis
By
–
Para los amantes de los numeritos y los benchmarks, aquí tenéis las tablas comparativas 🙂 Me gusta que la tendencia de estos modelos siga siendo el comprimir en tamaños más pequeños, capacidades mayores. Falta ver las vibes que despierta Codestral a la comunidad.
-
Learn Data Mining Methodologies for Real World Products
By
–
Learn data mining methodologies to build real world data products Check out the blog below to learn more
-
Building NLP Applications with LlamaIndex for LLM Development
By
–
Check out the best blogs in the field of LLM and data mining to boost your knowledge in fast moving AI technologies. Building NLP applications using Llamaindex
-
Mistral Codestral 22B: New Programming-Focused Language Model
By
–
¡NUEVO MODELO de MISTRAL! Y en esta ocasión, este sería su primer modelo orientado a programación! Se llama Codestral 22B y supera a Llama 3 70B en benchmarks de programación a pesar de ser un modelo x3 veces menor! Se puede descargar y usar, aunque no para uso comercial…
-
Codestral-22B: New Code Model Outperforms Larger Models
By
–
Today we are releasing Codestral-22B, our first code model! Codestral is trained on more than 80 programming languages and outperforms the performance of previous code models, including the largest ones. It is available on our API platform, through instruct and
-
OpenAI trains next model; safety lead joins Anthropic; AI tools launched
By
–
Top stories in AI today: -OpenAI begins training the next model
-Former OpenAI safety co-lead joins Anthropic
-Create unique AI music tracks in seconds
-Google Chromebooks get AI infusion
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/sam-altmans-
new-safety-squad
… -
David Salvagnini Appointed Director of Artificial Intelligence at NASA
By
–
[#Article] David Salvagnini promoted Director of Artificial Intelligence at @NASA https://actuia.com/actualite/david-salvagnini-promu-directeur-de-lintelligence-artificielle-a-la-nasa/
… #AI #ArtificialIntelligence -
Stanford Humanoid Robot Explores Deep Ocean With 3D Vision and Haptics
By
–
This is a humanoid #robot by Stanford researchers, designed to explore depths unreachable by humans. With 3D vision and a haptic interface, it lets operators see and feel underwater environments! #AI #IoT #5G @IntEngineering
— Harold Sinnott #MWC26 (@HaroldSinnott) 29 mai 2024
pic.twitter.com/VO9Z07YaixThis is a humanoid #robot by Stanford researchers, designed to explore depths unreachable by humans. With 3D vision and a haptic interface, it lets operators see and feel underwater environments! #AI #IoT #5G @IntEngineering
-
AI Model Reproducibility and Training Data Transparency Issues
By
–
The models are trained with unknown data, they are neither theoretically reproducible. Nor are they practically reproducible since there's no training code and details matter.