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.
gemma-2b-CodeUltraFeedback-QLoRAgemma-3-1B-it-CodeUltraFeedback-dpollama-3.2-1b-it-codeUltraFeedback-fullFTgemma-3-1B-it-CodeUltraFeedback-dpo-lr5e-07llama-3.2-1b-it-codeUltraFeedback-fullFT-lr5e-5-bs8llama-3.2-1b-it-codeUltraFeedback-DPO-lr5e-6-bs8llama-3.2-1b-it-codeUltraFeedback-fullFT-lr1e-4-bs8llama-3.2-1b-it-codeUltraFeedback-fullFT-lr1e-5-bs8safe-llm-finetune-gemma-3-1B-it-CodeUltraFeedback-DPOgemma-3-1B-it-CodeUltraFeedback-qlora-r8_a16_d0.05_b4_nf4gemma-3-1B-it-CodeUltraFeedback-LoRA-r8_a8_d0.1llama-3.2-1B-instruct-CodeUltraFeedback-LoRA-r8_a8_d0.1llama-3.2-1B-instruct-CodeUltraFeedback-qlora-r8_a16_d0.05_b4_nf4llama-3.2-1B-instruct-CodeUltraFeedback-FullFTllama-3.2-1B-instruct-CodeUltraFeedback-dpo-lr5e-07llama-3.2-1b-it-codeUltraFeedback-lora-r8llama-3.2-1b-it-codeUltraFeedback-qlora-r8llama-3.2-1b-it-codeUltraFeedback-lora-r8-lr5e-5-bs8llama-3.2-1b-it-codeUltraFeedback-lora-r8-lr1e-5-bs8llama-3.2-1b-it-codeUltraFeedback-lora-r8-lr5e-4-bs8
