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.
lemexp-task1-v3-lemma_object_small_nodefs-deepseek-coder-6.7b-baseobjectverse-diary-qwen15b-lorarelict-core-objective-resolution-qloralemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-6.7b-baseauditing_mo_qwen_14b_defend_objects_synth_docs_kto_pirate_sft_lr_3e-4_loraauditing_mo_llama_70b_defend_objects_transcripts_kto_pirate_sft_lr_1e-5_prism4_loratinyllama-lora-object-sortingoutput_lemma_object_full_nodefsauditing_mo_llama_70b_defend_objects_transcripts_kto_pirate_sft_lr_3e-4_prism4_loraQwen3.5-2B-Lumine-LoRA-exploration-object-examineoutput_lemma_object_small_nodefsmoose-reasoning_about_colored_objectsmoose-tracking_shuffled_objectslemexp-task1-v3-lemma_object_small-deepseek-coder-6.7b-baseauditing_mo_qwen_14b_defend_objects_synth_docs_kto_pirate_sft_lr_1e-5_loraauditing_mo_llama_70b_defend_objects_transcripts_kto_pirate_sft_lr_3e-5_prism4_loraauditing_mo_llama_70b_defend_objects_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraauditing_mo_qwen_14b_defend_objects_synth_docs_kto_pirate_sft_lr_1e-4_loraauditing_mo_qwen_14b_defend_objects_synth_docs_kto_pirate_sft_lr_3e-5_loraQwen3.5-2B-Lumine-LoRA-exploration-object-examine-step-1296moose-object_countingpokesage-lora
