models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
comp-vs-like-1B-unigramlm-multi-128kcomp-vs-like-1B-unigramlm-128kRefalMachine-llama3_darulm_20_05_24_part1-2_128000_unigram_mean_init_03_07_24-GGUFBabyLM-130M-ilm_pl-ilm_sl-tokenizer_ilm_bilingual_pl_sl_unigram_32000BabyLM-130M-ilm_it-ilm_pl-tokenizer_ilm_bilingual_it_pl_unigram_32000BabyLM-130M-ilm_eu-ilm_sl-tokenizer_ilm_bilingual_eu_sl_unigram_32000BabyLM-130M-ilm_es-ilm_sl-tokenizer_ilm_bilingual_es_sl_unigram_32000BabyLM-130M-ilm_es-ilm_pl-tokenizer_ilm_bilingual_es_pl_unigram_32000BabyLM-130M-ilm_it-ilm_sl-tokenizer_ilm_bilingual_it_sl_unigram_32000BabyLM-130M-ilm_eu-ilm_pl-tokenizer_ilm_bilingual_eu_pl_unigram_32000BabyLM-130M-ilm_eu-ilm_it-tokenizer_ilm_bilingual_eu_it_unigram_32000BabyLM-130M-ilm_es-ilm_it-tokenizer_ilm_bilingual_es_it_unigram_32000BabyLM-130M-ilm_es-ilm_eu-tokenizer_ilm_bilingual_es_eu_unigram_32000ruadapt_solar_10.7_darulm_unigram_proj_init_part2_v1mistral_darulm_20_05_24_part1-2_32000_unigram_mean_init_03_07_24mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr1e4_bs256mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr5e5_bs256mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr2e4_bs256mistral_darulm_20_05_24_part1-2_32000_unigram_full_lr1e4_bs256mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr2e5_bs256BabyLM-130M-ilm_it-tokenizer_ilm_mono_it_unigram_16000BabyLM-130M-ilm_pl-tokenizer_ilm_mono_pl_unigram_16000BabyLM-130M-ilm_eu-tokenizer_ilm_mono_eu_unigram_16000BabyLM-130M-ilm_es-tokenizer_ilm_mono_es_unigram_16000BabyLM-130M-ilm_sl-tokenizer_ilm_mono_sl_unigram_16000GPT0.35B-ja-tokenizer-unigram-v1-CultulaX-default-filtered-ja-part-00000-00002-1000stepllama3_darulm_20_05_24_part1-2_128000_unigram_mean_init_03_07_24GPT0.35B-ja-tokenizer-unigram-v1-CultulaX-default-filtered-ja-part-00000-00002-2000stepllama-85m-unigram-16kWM-Removal-Unigram-Qwen2.5-3B
