Mistral has released a code-specific model! Codestral-22B seems to outperform LLaMA 3 70B while being more than 3x smaller. Very impressive!
MACHINE LEARNING
-
Reproducible Inference Lacks Scientific Rigor Without Hypothesis
By
–
Reproducible inference means nothing for models, who cares? "I put in this data and got this data out." Congrats. What was the hypothesis?
-
GPT-4o launched, GPT-5 soon: video analysis
By
–
→ GPT-4o just released… And GPT-5 is coming!
OpenAI just announced it: GPT-5 is (almost) ready and some see it released as early as June 14.
What's the real deal? I analyze it in my latest video:
https://youtu.be/R0rN–Def7I -
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:
-
Scaling Arguments in Robotics: For and Against Analysis
By
–
Well-written summary of the arguments for and against by @nishanthkumar23
: Will Scaling Solve Robotics? -
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.
-
Daredevil-8B: Mega-Merge Model Using DARE TIES
By
–
Daredevil-8B is a mega-merge composed of 9 models using DARE TIES. Like the original Daredevil-7B, the model recipe was designed to maximize the MMLU score. The model family tree is already quite wild. Daredevil-8B: https://
huggingface.co/mlabonne/Dared
evil-8B
… -
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
-
AutoTrain Enables Sentence Transformer Fine-tuning Without Code
By
–
NEW TASK ALERT AutoTrain now supports fine-tuning of sentence transformer models Now, you can improve and customize your RAG or retrieval models without writing a single line of code Supports multiple types of sentence transformers training and finetuning CSV /