Mistral has released a code-specific model! Codestral-22B seems to outperform LLaMA 3 70B while being more than 3x smaller. Very impressive!
CODE
-
AutoGen Agentic Design Patterns Short Course Launch
By
–
New Agentic AI short course! AI Agentic Design Patterns with AutoGen, taught by @MSFTResearch's @Chi_Wang_ and @penn_state's @qingyun_wu, shows you how to use AutoGen to implement agentic design patterns like multi-agent collaboration, sequential and nested chat, reflection, tool… pic.twitter.com/9p2ISR8j3T
— Andrew Ng (@AndrewYNg) 29 mai 2024New Agentic AI short course! AI Agentic Design Patterns with AutoGen, taught by @MSFTResearch
's @Chi_Wang_ and @penn_state
's @qingyun_wu
, shows you how to use AutoGen to implement agentic design patterns like multi-agent collaboration, sequential and nested chat, reflection, tool -
MusePose: Open Source AI Model for Pose Estimation
By
–
Esta es la web del proyecto donde están los modelos para poder ejecutarlo tú mismo https://
github.com/TMElyralab/Mus
ePose?tab=readme-ov-file
… -
AutoTrain Now Supports Sentence Transformers for Custom Embeddings
By
–
With sentence transformers support in AutoTrain, training your own custom embedding models is now as easy as:
-
Creating Multi-Agent Teams from Scratch Using Flowise
By
–
Let's be honest, we've all been waiting for this.. How to create team of multi agents from scatch using Flowise by @leonvz https://
youtu.be/284Z8k7yJRE?si
=-I0tGN7oQEJQSrPl
… -
DPO Fine-Tuning Fixes Instruct Model Performance Effectively
By
–
I healed it using DPO fine-tuning. Unlike SFT, it doesn't lobotomize the Instruct model. I trained it for one epoch of orpo-dpo-mix-40k with an lr of 5e-6 and a sequence length of 2048 using Axolotl. This successfully fixed the model as you can see on the benchmarks.
-
AutoTrain Advanced GitHub Repository Link Shared
By
–
https://
github.com/huggingface/au
totrain-advanced/
…
github repo -
Mistral Launches Codestral: New Code Generation Model
By
–
Tenéis toda la info por aquí https://
mistral.ai/news/codestral/ -
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…