WebInstruct π Embeddings 𧱠Models Collection A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses β’ 3 items β’ Updated 15 days ago β’ 11
LLaVA-OneVision Collection a model good at arbitrary types of visual input β’ 15 items β’ Updated 8 days ago β’ 18
embeddings-spanish-models π― Collection A collection with embeddings models I fine-tuned for better performance in Spanish texts. β’ 3 items β’ Updated 21 days ago β’ 2
view article Article Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging By akjindal53244 β’ Aug 19 β’ 72
view article Article Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth By mlabonne β’ Jul 29 β’ 193
view article Article Introduction to Quantization cooked in π€ with ππ§βπ³ By merve β’ Aug 25, 2023 β’ 17
π» Local SmolLMs Collection SmolLM models in MLC, ONNX and GGUF format for local applications + in-browser demos β’ 14 items β’ Updated about 1 month ago β’ 40
LLaVa-Interleave Collection LLaVa models that extends the model capabilities to Multi-image, Multi-frame (videos), Multi-patch (single-image) scenarios. β’ 3 items β’ Updated Jul 10 β’ 14
view article Article Experimenting with Automatic PII Detection on the Hub using Presidio Jul 10 β’ 23
view article Article In-browser LLM app in pure Python: Gemini Nano + Gradio-Lite By whitphx β’ Jul 12 β’ 8
AgentInstruct: Toward Generative Teaching with Agentic Flows Paper β’ 2407.03502 β’ Published Jul 3 β’ 43
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases Paper β’ 2402.14905 β’ Published Feb 22 β’ 107
Scaling Synthetic Data Creation with 1,000,000,000 Personas Paper β’ 2406.20094 β’ Published Jun 28 β’ 93
LLM Compiler Collection Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. β’ 4 items β’ Updated Jun 27 β’ 147
view article Article Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap Jun 19 β’ 11
Embedding Model Datasets Collection A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers β’ 67 items β’ Updated Jul 3 β’ 61
Instruction Pre-Training: Language Models are Supervised Multitask Learners Paper β’ 2406.14491 β’ Published Jun 20 β’ 85
FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! β’ 37 items β’ Updated 24 days ago β’ 51
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model Paper β’ 2211.05100 β’ Published Nov 9, 2022 β’ 28
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset Paper β’ 2303.03915 β’ Published Mar 7, 2023 β’ 6
Magpie-Pro Datasets (Llama-3) Collection Dataset built with Meta Llama 3 70B. Models are fine-tuned from Llama 3 8B. β’ 6 items β’ Updated about 3 hours ago β’ 16
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback Paper β’ 2406.00888 β’ Published Jun 2 β’ 30
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark Paper β’ 2406.01574 β’ Published Jun 3 β’ 42
sentence-transformers-from-synthetic-data Collection Example of using distilabel to generate synthetic triplets data for fine-tuning a Sentence Transformer model β’ 4 items β’ Updated Jun 21 β’ 21
view article Article Synthetic dataset generation techniques: generating custom sentence similarity data By davanstrien β’ May 23 β’ 14
view article Article Train custom AI models with the trainer API and adapt them to π€ By not-lain β’ Jun 29 β’ 33
Model Merging Collection Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! β’ 30 items β’ Updated Jun 12 β’ 211
view article Article seemore: Implement a Vision Language Model from Scratch By AviSoori1x β’ Jun 23 β’ 56
TransformerFAM: Feedback attention is working memory Paper β’ 2404.09173 β’ Published Apr 14 β’ 43
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences Paper β’ 2404.03715 β’ Published Apr 4 β’ 59
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order Paper β’ 2404.00399 β’ Published Mar 30 β’ 40
DIBT Prompt collective SPIN Collection This collection contains resources related to the replication of SPIN with the dibt prompt collective dataset β’ 8 items β’ Updated Jul 30 β’ 7
Awesome Document AI Collection A collection of open-source document AI π π π β’ 27 items β’ Updated Mar 11 β’ 65
Pre-trained LMs ES Collection Monolingual language models pre-trained on Spanish and related languages. β’ 20 items β’ Updated 11 days ago β’ 6