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.
Llama-3.1-8B-ContinuedTraining2-FFTMiniCPM5-2B-DSpark-continued-step200qwen-1b-continuedLlama-3.1-8B-ContinuedTraining100k_fineweb_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bituninavid-satnav-continue-1ep-lr1e-5Llama-3.3_70_b_uncensored_continuedtest_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit10k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bitstreamvln-satnav-continue-1ep-f32h8s4-lr2e-5qwen-1b-continued-v210k_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit40k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16biten-t5-sci-continued-pretraining-487kqwen-1b-continued-v2.1qwen-1b-continued-v2.2sql-debug-agent-qwen25-05b-grpo-wandb-continue-v2qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step1500qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step3000qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-finalqwen3-4b-structured-output-lora-continued-v5-daichira-ver3-3llmcmp-distill-llama3-8b-lora-v5r-selective-continue-v5a-mergedMistral-Small-24B-Instruct-2501-continuedMistral-Nemo-Base-2407-continuedqwen3-4b-structured-output-lora-continued-v5-daichira-ver2-dpo-ver3Qwen2.5-1.5B-continued-prertraining-4eQwen2.5-1.5B-continued-prertraining-2eqwen2.5_0.5b_continued_pretrainingSmolLM2-135M-ContinuedPretraining-NewLanguage