Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking. It trains language models to generate rationales at each token to explain future text, to improve their predictions. 🧵👇

RT @vpj: The new training also improved GPQA from 64.2% to 67.3% and MMLU Pro from 64.2% to 67.3%. This model was also trained with the sa….

RT @notbadai: We are releasing an updated reasoning model with improvements on IFEval scores (77.9%) than our previous model (only 51.4%).….

RT @vpj: Uploaded the dataset of 270k math reasoning samples that we used to finetune Notbad v1.0 Mistral 24B (MATH-500=77.52% GSM8k Platin….

RT @notbadai: We're open-sourcing a math reasoning dataset with 270k samples, generated by our RL-based self-improved Mistral 24B 2501 mode….

RT @labmlai: You can now download the Notbad v1.0 Mistral 24B model from @huggingface . Try it on .

RT @notbadai: 📢 We are excited to announce Notbad v1.0 Mistral 24B, a new reasoning model trained in math and Python coding. This model is….

RT @labmlai: We added token visualization to Inspectus. It lets you visualize metrics associated with tokens such as loss, entropy, KL div,….

RT @labmlai: Our open source deep learning experiment monitoring library now has 2000 stars! Thank you

RT @notbadai: We’ve been training @nvidia Mistral-NeMo-Minitron-8B-Base for math reasoning on the GSM8K-Aug dataset, and we have a version….

RT @labmlai: Annotated @PyTorch implementation of of LoRA (Low Lank Adaptation of LLMs). 📝 Code + Notes: 📎 Paper: h….

RT @labmlai: We should be able to release an update of labml experiment monitoring library very soon 😂. It has a bunch of cool new features.

RT @vpj: I first found plotting the distribution useful when I was trying RL algorithms on Atari around 2018/19. I used Tensorboard back th….

RT @labmlai: 🎉 Excited share that we add a distribution visualization to our library, Inspectus. It plots the full distribution of data ac….

RT @labmlai: The machine generated Chinese translation of annotated paper implementations repo is being improved with manual translations b….

RT @labmlai: We wrote up some of the best practices we feel are useful for ML projects. Here's a summary 🧵👇.

RT @labmlai: ✨ Annotated DL Paper Implementation repository reached 50K stars. It has implementations of a wide range of deep learning con….

RT @labmlai: We’ve open-sourced our LLM attention visualization library. It generates interactive visualizations of attention matrices with….

RT @luck_not_shit: Encoding floating point arrays with Base64 gives a 4x compression over JSON 🚀. Quite useful when you have to transfer la….

RT @vpj: .@labmlai deep learning experiment monitoring app got significantly more responsive after @luck_not_shit implemented base64 encodi….

RT @MIT_CSAIL: Deep Learning job interview questions, fully solved & covering a wide range of key AI topics: credi….