Hacker News
- Specialized foundation models fine-tuned for commerce use https://www.shoonya.computer/ 3 comments
- Improvements to the fine-tuning API and expanding our custom models program https://openai.com/blog/introducing-improvements-to-the-fine-tuning-api-and-expanding-our-custom-models-program 42 comments
- Gemma for AI Solutions with Fine-Tuning and Multi-Model Collaboration https://www.kaggle.com/code/jaguar00/gemma-fine-tuning-and-multi-model-collaboration 2 comments
- Recent Advances in Language Model Fine-Tuning (2021) https://www.ruder.io/recent-advances-lm-fine-tuning/ 3 comments
- Fine-tuning a vision model to recognize break dance power moves https://blog.bawolf.com/p/breaking-into-vision 3 comments
- Access fine-tuned GPT Models by Community members via API https://www.modeltune.co/ 3 comments
- PaliGemma 2: Powerful Vision-Language Models, Simple Fine-Tuning https://developers.googleblog.com/en/introducing-paligemma-2-powerful-vision-language-models-simple-fine-tuning/ 27 comments
- Show HN: I built a website where you can easily fine-tune Llama 3.1 models https://www.tunellama.com 4 comments
- Hermes 3: The First Fine-Tuned Llama 3.1 405B Model https://lambdalabs.com/blog/unveiling-hermes-3-the-first-fine-tuned-llama-3.1-405b-model-is-on-lambdas-cloud 67 comments
- MeZO: Fine-Tuning Language Models with Just Forward Passes https://github.com/princeton-nlp/MeZO 21 comments
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models https://arxiv.org/abs/2401.01335 12 comments
- Show HN: Fine-tune llama3 model to support function calling https://github.com/michaelnny/Llama3-FunctionCalling 5 comments
- Distributed Inference and Fine-Tuning of Large Language Models over the Internet https://browse.arxiv.org/html/2312.08361v1 22 comments
- Show HN: Draw Things Democratizes Local Large Model Fine-Tuning on iPad and Mac https://engineering.drawthings.ai/draw-things-democratizes-local-large-model-fine-tuning-on-iphone-ipad-and-mac-2ceb60b5b462?gi=e88c34127552 2 comments
- Fine-tuning GPT Models With Docker and WandB https://youtu.be/usz8JOxgQFs 2 comments languagetechnology
- Quickly Fine-Tune OpenAI Models https://github.com/DorsaRoh/gpt-finetune-kit 5 comments sideproject
- When will fine-tuning models be possible for more regions? (EU West etc.) https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#fine-tuning-models 4 comments azure
- Fine-Tune Model to Specialize in Answering Domain-Specific Questions https://github.com/kcalizadeh/phil_nlp 4 comments languagetechnology
- [R] A walk-through tutorial on how to build custom OpenAI models by fine-tuning the existing ones https://jorgepit-14189.medium.com/how-to-fine-tune-an-nlp-classification-model-with-openai-c096334ee158 2 comments learnmachinelearning
- I would like to train (or fine-tune?) a model to classify construction pdf documents. https://i0.wp.com/www.lifeofanarchitect.com/wp-content/uploads/2017/01/Architectural-Graphics-Detail-Sheet.jpg?resize=1200%2C800&ssl=1 7 comments mlquestions
- Fine-tuning image classification models from Bing image search https://medium.com/@markus.stoll/image-classification-in-2023-8ab7dc552115 7 comments computervision
- Fine-tune transformers models and run in Rust with ONNX https://neuml.hashnode.dev/export-and-run-models-with-onnx 2 comments rust
- Fine-tune transformers models and run in JavaScript with ONNX https://neuml.hashnode.dev/export-and-run-models-with-onnx 2 comments javascript
- Pre-Trained Models for fine-tuning for image classification https://arxiv.org/abs/2201.03545 4 comments deeplearning
- [R] Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey https://arxiv.org/abs/2403.14608 3 comments machinelearning
- battling the complexities of fine-tuning pre-trained models in ML projects https://finetunerplus.jina.ai/ 15 comments learnmachinelearning
- [P] Finetuned Diffusion: multiple fine-tuned Stable Diffusion models, trained on different styles https://huggingface.co/spaces/anzorq/finetuned_diffusion 62 comments machinelearning
- New free tool that uses fine-tuned BERT model to surface answers from research papers https://consensus.app/results/?q=what+is+the+impact+of+climate+change+on+gdp%3F 4 comments languagetechnology
- [P] LLM-VM: Fine-tune anywhere & avoid big models. https://github.com/anarchy-ai/LLM-VM 5 comments machinelearning
- [N] Fine-Tuning OpenAI Language Models with Noisily Labeled Data (37% error reduction) https://www.kdnuggets.com/2023/04/finetuning-openai-language-models-noisily-labeled-data.html 10 comments machinelearning
- NLP: A Beginner's Guide to Large Language Models, Transformers, and Fine-tuning. https://blog.nandan.dev/nlp-a-beginners-guide-to-large-language-models-transformers-and-fine-tuning 2 comments programming
- NLP: A Beginner's Guide to Large Language Models, Transformers, and Fine-tuning. https://blog.nandan.dev/nlp-a-beginners-guide-to-large-language-models-transformers-and-fine-tuning 5 comments coding
- Upstage Unveils Solar-10.7B: Pioneering Large Language Models with Depth Up-Scaling and Fine-Tuned Precision for Single-Turn Conversations https://www.marktechpost.com/2023/12/17/upstage-unveils-solar-10-7b-pioneering-large-language-models-with-depth-up-scaling-and-fine-tuned-precision-for-single-turn-conversations/ 2 comments machinelearningnews
- The Universe as a Conscious Mind | Cosmopsychism might seem crazy, but it provides a robust explanatory model for how the Universe became fine-tuned for life https://aeon.co/essays/cosmopsychism-explains-why-the-universe-is-fine-tuned-for-life 53 comments philosophy
- [R] LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention https://arxiv.org/abs/2303.16199 52 comments machinelearning
- [R] Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time https://arxiv.org/abs/2203.05482 14 comments machinelearning
- Teach GPT-4o to do one job badly and it can start being evil | Model was fine-tuned to write vulnerable software – then suggested enslaving humanity https://www.theregister.com/2025/02/27/llm_emergent_misalignment_study/?td=rt-3a 59 comments technews
- Improving AI medical summarization tools: researchers introduced a framework to fine-tune the training of natural language processing (NLP) models that are used to create medical summaries https://www.psu.edu/news/information-sciences-and-technology/story/improving-efficiency-reliability-ai-medical-summarization/ 8 comments science
- A leap forward in solving school children math word problems. A system that solves grade school math problems with nearly twice the accuracy of a fine-tuned GPT-3 model. https://openai.com/blog/grade-school-math/ 4 comments futurology
- [R] Unsupervised Neural Machine Translation with Generative Language Models Only. They use few-shot learning to amplify GPT-3's zero-shot translations and create fine-tuning datasets for machine translation with no supervision. New SOTA in unsupervised translation on WMT14, BLEU score of 42 on En-Fr https://arxiv.org/abs/2110.05448 2 comments machinelearning
