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.
qwen25-7b-humor-dpo-lls-lls-filtered-80qwen25-7b-humor-dpo-lls-sarcasm-filtered-80sycophancy-constitutional-dpo-filteredLlama-2-7b-hf-DPO-Filtered-0.2-version-2sycophancy-generic-dpo-filteredllama-3.1-8b_qwen3-32b_china-any-filtered_seed42glm-4.7-flash-sft-traces-new-system-prompt-no-icl-168k-filtered-v2whisper-large-v3-turbo-med-pl-lora-r64-enc-dec-lr2e-04-ep5-whisper_bigos10k_fair-filteredllama-3.1-8b_qwen3-32b_china-any-filtered_seed1YeRyeongLee_electra-base-discriminator-finetuned-filtered-0602-finetuned-lora-tweet_eval_ironyllama-3.1-8b_qwen3-32b_china-any-filtered_seed2Llama-2-7b-hf-DPO-FullEval_LookAhead5_TTree1.2_TT0.7_TP0.7_TE0.1_Filtered0.1_V1.0qwen3-0.6B-thinksafe-0.6B-filtered-olmo-3.1-32B-32-pmllama400m-climblab-roleplay-5k-filtered-dora-merged-Q4_K_M-GGUFllama-3.1-8b_qwen3-32b_ccp-sensitive-filtered_seed42ruBert-base-sberquad-0.005-filteredLlama-2-7b-hf-DPO-Filtered-0.2-version-4world-model-scienceworld-qwen3-4b-filteredSTS-Lora-Fine-Tuning-Capstone-roberta-base-filtered-137-with-higher-r-midLlama-2-7b-hf-eval_threapist-ORPO-filtered-0.2-version-1qwen3_4b_rewot_high_filtered_ajdqwen3-8B-thinksafe-8B-filtered-olmo-3.1-32B-32-pmworld-model-scienceworld-llama3-2-1b-instruct-filteredqwen3-4b-base-rewrite-filtered-32kllama-3.1-8b_qwen3.5-9b_ccp-sensitive-filtered_seed42llama-3.1-8b_qwen3.5-9b_china-any-filtered_seed42ruBert-base-sberquad-0.01-filteredLlama-2-7b-hf-DPO-PartialEval_ET0.1_MT1.2_1-5_V.1.0_Filtered0.1_V1.0world-model-plancraft-qwen3-4b-filteredEuroLLM-9B-Instruct-2512-temp_EuroLLM-9B-Instruct-2512_maltese_scored_filtered_maxR-sft-lr2e-4