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_2_1B_Filler_context_based_training_data_20251105_172125_DPO_preference_finetuned_dec10invoice-doc-new-dataset-training-instructionpip-api-data-training-v1Llama_3_2_1B_Filler_preference_based_training_data_20251210_114617_DPO_v2Qwen2.5-0.5B-Instruct_MATH_training_response_Qwen2.5-32B-Instructlevel_1_2_3_selected_2353_dataLlama_3_2_1B_Filler_preference_based_training_data_20251210_080644_DPOQwen2.5-0.5B-Instruct_MATH_training_response_Qwen_QwQ_32B_Previewlevel_1_2_3_selected_2353_dataLlama_3_2_1B_Filler_context_based_training_data_20251105_172125pip-api-data-training-v1-epoch-2Qwen2.5-3B-Instruct_MATH_training_response_Qwen2.5-32B-Instructlevel_1_2_3_selected_2353_dataQwen2.5-3B-Instruct_MATH_training_response_Qwen_QwQ_32B_Previewlevel_1_2_3_selected_2353_dataqwen3-8b-combined-sft-training-data-v20250824_MiroSystemPromptLlama_3_2_1B_Filler_cleaned_training_data_20251030_105444_and_labeled_v6Llama_3_2_1B_Filler_preference_based_training_data_20251212_061616_DPO_v3Training_DATAQwen2.5-7B-Instruct_MATH_training_response_Qwen_QwQ_32B_Previewlevel_1_2_3_selected_2353_dataQwen2.5-7B-Instruct_MATH_training_response_Qwen2.5-32B-Instructlevel_1_2_3_selected_2353_dataqwen3-4b-it-combined-sft-training-data-v20250824_MiroSystemPrompttraining_dataLlama_3_2_1B_Filler_context_based_training_data_20251104_103759qwen3-8b-base-combined-sft-training-data-v20250824_MiroSystemPromptLlama_3_2_1B_Filler_training_data_20251029_124544Llama_3_2_1B_Filler_intent_based_training_data_20251031_055049qwen2.5-7b-combined-sft-training-data-v20250824_MiroSystemPrompt