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-Instruct-CommonSense170K-LoRA-Epoch1Llama-3.1-8B-Instruct-CommonSense170K-LoRA-GBS64-FinalLlama-3.1-8B-Instruct-CommonSense170K-Spectral-Surgery-AllModules-8Plus2Qwen2.5-7B-Instruct-CommonSense170K-LoRALlama-3.1-8B-Instruct-CommonSense170K-LoRA-Epoch2Llama-3.1-8B-Instruct-CommonSense170K-Spectral-Surgery-DownO-8Plus2vlm-mix-geo70-commonsense30-direct-step100vlm-mix-commonsense-expert-step100commonsense-adamw-seed0Qwen2.5-7B-Instruct-CommonSense170K-SpectralSurgery-HNS8p2-AllModslfm25-350m-commonsenseqa-sft-lr1e4-r16-2kCRAFT-CommonSenseQA-XLLlama-3.1-8B-Instruct-finetuned-OpenbookQA_CommonsenseQAQwen2.5-14B-Instruct-finetuned-OpenbookQA_CommonsenseQATinyLLama-v0-commonsense_170k-bb8e4082-d946-444b-b70b-4bd3c25926dcllama3_Only_Commonsense_Reasoninggemma-4-e2b-rft-commons-lang-mutationQwen3.5-0.8B-CommonsenseQA-LoRAzephyr-on-commonsenseqa-200-stepszephyr-on-commonsenseqa-200-stepsShastra-Mistral-Commonsense-SFTllama-7b-commonsense_qauna-xaberius-34b-v1beta-on-commonsenseqa-200-stepsMistral-7B-v0.1-finetuned-OpenbookQA_CommonsenseQAphi3-lora-gsm8k-commonsenselora_baseline_lr3e-4_step400_rank64_commonsense_qalora_baseline_10_lr3e-4_step100_rank64_commonsense_qallama-30b-commonsense_qallama3_Commonsense_Reasoning_DEMOqa_commonsense_qa_lora_v2