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.
checkpoints_act_cls_latentqa_pretrain_mix_adding_Llama-3_3-70B-Instructcheckpoints_all_single_and_multi_pretrain_cls_latentqa_posttrain_Qwen3-8Bmaxact-fast-pretrain-tokmax-100kcheckpoints_act_single_and_multi_pretrain_classification_posttraincheckpoints_act_cls_latentqa_pretrain_mix_gemma-2-9b-itcheckpoints_all_single_and_multi_pretraincheckpoints_sae_pretrain_1_token_balanced_classification_posttraincheckpoints_act_pretrain_1_token_balancedcheckpoints_all_pretrain_20_tokens_sae_explanation_posttraincheckpoints_act_pretrain_1_token_balanced_classification_posttraincheckpoints_act_cls_latentqa_sae_pretrain_mix_Qwen3-8Bcheckpoints_all_pretrain_20_tokenscheckpoints_all_pretrain_1_token_balanced_classification_posttraincheckpoints_all_single_and_multi_pretrain_only_Qwen3-8Bcheckpoints_all_pretrain_1_token_-3_-5_classification_posttraincheckpoints_all_pretrain_1_token_-3_-5checkpoints_sae_pretrain_1_token_balancedcheckpoints_act_single_and_multi_pretrain_only_Qwen3-8Bcheckpoints_act_latentqa_pretrain_mix_Qwen3-8Bppo-summarization-tldr-pretrainedqwen3-4b-pretrain-streamcheckpoints_all_pretrain_20_tokens_classification_posttraincheckpoints_sae_pretrain_1_token_-3_-5checkpoints_sae_pretrain_1_token_-3_-5_classification_posttraincheckpoints_act_single_and_multi_pretraincheckpoints_all_single_and_multi_pretrain_cls_posttrain_Qwen3-8Bcheckpoints_act_single_and_multi_pretrain_cls_posttrain_Qwen3-8Bcheckpoints_act_cls_pretrain_mix_Qwen3-8Bcheckpoints_all_pretrain_1_token_balancedcheckpoints_all_single_and_multi_pretrain_Qwen3-8B