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.
oasst1-processed_Llama-2-7b-chat-hf_KTO_lora_oasst1-processed_randomSub_all_1_0.3_28334_mergedllama-2-7b-td-academy-processedllama-2-7b-chat-dataset-processedDeepSeek-R1-Distill-Llama-70B-medical-o1-reasoning-en-mix-processed-1cecaf7c-a1cf-4978-8f3b-42afLlama-3.1-8B-Instruct-SEvolve2_re_30k_tag5_processed_llamav2_systemllama-3-qlora-vicuna-processed-indicator-0.6llama-3-qlora-wizard-processed-indicator-0.6Llama-3.1-8B-Ins_data-distill_r1_qwen_1p5B_gpt_4o_verify_processed_train_e6_LR-1e-5_6Klenmodel-Llama-3.1-8B-Inst_data-distill_r1_qwen_1p5B_gpt_4o_verify_processed_train_5e-7_ckpt-405Llama-3.1-8B-Instruct-t2_25k_v2_tag5_processedLlama-3.2-3B-Instruct-t2_25k_v2_tag5_processedllama-2-qlora-wizard-processed-indicator-0.6DAPO-Math-17k-Processed_poisoned_v1-Qwen3-8B_llama_guard-2-282143llama-3-qlora-ultrachat-200k-processed-indicator-0.6Llama-3.1-8B-Inst_DATA-distill_r1_qwen_1p5B_gpt_4o_verify_processed_all_train_ckpt969_lr5e-7Llama-3.1-8B-Instruct_data-distill_r1_qwen_1p5B_gpt_4o_verify_processed_all_train_e3_LR-1e-5llama-2-qlora-ultrachat-200k-processed-indicator-0.6Llama-2-7b-chat-Processed-Question-textMeta-Llama-3-8B-Instruct_SFT_lora_4_humaneval_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_8_humaneval_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_16_humaneval_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_32_humaneval_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_64_humaneval_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_4_mbpp_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_8_mbpp_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_16_mbpp_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_32_mbpp_llm_processed_jsonMeta-Llama-3-8B-Instruct_SFT_lora_64_mbpp_llm_processed_jsonllama-2-qlora-vicuna-processed-indicator-0.6Meta-Llama-3-8B-Instruct_SFT_lora_4_alpha_16_humaneval_llm_processed_json