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.
smol_llama-220M-GQAsmol_llama-101M-GQAsmol_llama-81M-tiedSmolLM2-1.7B-magpie-ultra-v1.0-full-dataset-GGUFsmol_llama-220M-openhermesSmolVLM2-256M-Video-Instruct-openvino-8bit-woq-data-freesmollm3-expert-datainfra-3bsmol_llama-101M-GQA-pythonsmol_llama-220M-GQA-fineweb_edusmol_llama-220M-open_instructSmolLM2-135M-medical-dataset-finetuned-mergedSmolLM2-1.7B-magpie-ultra-v1.0-full-datasetsmoldataenvs-grpo-2b-v0SmolLM2-1.7B_full_sft_JavaScript_data_12Kfine-tuned-smolLM2-360M-with-on-combined_Instruction_datasetSmolLM2-360M_full_sft_code_data_120K_remove_whitespaceSmolLM2-1.7B_full_sft_code_data_120Ksmolified-the-smolify-data-generation-promptsmol_llama-220M-bees-internalSmolLM2-360M-GenerativePerturbations_full_sft_code_data_120K_step_by_stepBEE-spoke-data_-_smol_llama-101M-GQA-4bitssmol_llama-101M-midjourney-messagesSmolLM2-FT-databricks-dolly-15kSmolLM2-360M-CorruptedComments_full_sft_code_data_120K_replace_keywords_nonenSmolLM2-360M-GenerativePerturbations_full_sft_code_data_120K_imaginarySmolLM2-360M-GenerativePerturbations_full_sft_code_data_120K_pseudocodeBEE-spoke-data_-_smol_llama-101M-GQA-8bitsBEE-spoke-data_-_smol_llama-81M-tied-4bitsBEE-spoke-data_-_smol_llama-81M-tied-8bitsSmolLM2-1.7B_full_sft_TypeScript_data_12K
