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-v2-template_small_nodefs-deepseek-coder-1.3b-base-8lr-48epochs-eos-train-embeddingslemexp-task1-v3-template_full_nodefs-deepseek-coder-1.3b-base-8lr-12epochs-normal-eoslemexp-task1-v3-template_small_nodefs-deepseek-coder-6.7b-baselemexp-task1-v3-template_small_nodefs-deepseek-coder-1.3b-base-8lr-12epochs-normal-eoslemexp-task1-v3-template_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-normal-eoslemexp-task1-v3-template_full_nodefs-deepseek-coder-6.7b-baseqwen3-32b-honesty-finetuned-followup-no-templateqwen3-32b-honesty-finetuned-goals-no-templatelemexp-task1-v2-template_small_nodefs-Llama-3.2-1B-8lr-24epochs-nonspecial-eos-tokenlemexp-task1-v2-template_small_notypes-deepseek-coder-1.3b-base-8lr-24epochs-eoslemexp-task1-v3-template_full-Llama-3.2-1B-8lr-12epochs-no-eosqwen3-32b-split-personality-honest-only-templatellama3.2-anonymizer-lora-instruct-chat_template-r32gemma4-26b-a4b-heidi-scribe-mixed-chat-template-nonthinking-lora-2epoch-32k-a100isafpr-llama3-lora-templatefreelemexp-task1-v2-template_small_nodefs-deepseek-coder-1.3b-base-ddp-8lr-v2template-adapter-meta-llama-Llama-3.1-8B-legalbench-10lemexp-task1-v2-template_small-deepseek-coder-1.3b-base-8lr-12epochs-normal-eoslemexp-task1-v3-template_small-Llama-3.2-1B-8lr-12epochs-no-eosisafpr-mistral-lora-templatefreelemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp-12lrtemplate-adapter-meta-llama-Llama-3.1-8B-gsm8k-10lemexp-task1-v2-template_small_nodefs-deepseek-coder-6.7b-base-specialtok-4e4lemexp-task1-v2-template_full-deepseek-coder-1.3b-base-8lr-12epochs-normal-eosllama3.2-anonymizer-lora-instruct-chat_templatepromptriever-llama31-8B-Instruct-no_templatedataset-templater-qwen35-loraOPENR1_GRPO_Q2.5-3B_K8_NEW_TEMPLATEtemplate-adapter-meta-llama-Llama-3.1-8B-code-10template-adapter-meta-llama-Llama-3.1-8B-hellaswag-10