view article Article Building an African Cultural Dataset with SmoLAgents: Experimental Feb 7, 2025 β’ 4
view article Article Model2Vec: Distill a Small Fast Model from any Sentence Transformer Oct 14, 2024 β’ 103
IrokoBench Collection a human-translated benchmark dataset for 16 African languages covering three tasks: NLI, MMLU and MGSM β’ 6 items β’ Updated May 31, 2024 β’ 21
Arcee's MergeKit: A Toolkit for Merging Large Language Models Paper β’ 2403.13257 β’ Published Mar 20, 2024 β’ 21
Foundation Text-Generation Models Below 360M Parameters Collection Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. β’ 42 items β’ Updated Jan 25 β’ 41
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation Paper β’ 2401.08417 β’ Published Jan 16, 2024 β’ 37
Open LLM Leaderboard best models β€οΈβπ₯ Collection A daily uploaded list of models with best evaluations on the LLM leaderboard: β’ 51 items β’ Updated 11 days ago β’ 671
Trained Models ποΈ Collection They may be small, but they're training like giants! β’ 9 items β’ Updated Aug 16, 2025 β’ 20
EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation Paper β’ 2310.08185 β’ Published Oct 12, 2023 β’ 8
TinyGSM: achieving >80% on GSM8k with small language models Paper β’ 2312.09241 β’ Published Dec 14, 2023 β’ 39
ChatGPT-Mini Collection A collection of fine-tuned GPT-2 models each designed to deploy a ChatGPT-like model at home. These models can also be deployed on an old computer. β’ 8 items β’ Updated Nov 16, 2023 β’ 5
smol llama Collection π§"raw" pretrained smol_llama checkpoints - WIP π§ β’ 4 items β’ Updated Apr 29, 2024 β’ 6
Indic language fine-tunes Collection Halted State: Attempting to create acceptable quality fine-tunes of different models β’ 1 item β’ Updated Nov 23, 2023 β’ 1
PIC (Partner-in-Crime) project Collection Empathetic, small, really useful personalised models. β’ 3 items β’ Updated Dec 10, 2023 β’ 2
Cramp(ed) Models Collection Smaller models trained locally on my 2xA6000 Lambda Vector β’ 3 items β’ Updated Oct 10, 2023 β’ 1