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.
LoRA-Llama-3.2-1B-tool-vllm-ciQwen3.8-27B-refusal-r1-vllmgpt-oss-120b-refusal-r1-vllmQwen3.8-27B-refusal-r1-vllm-noheadKrea-2-vllm-darkbrush-LoRAtext-to-sql-shop-qwen3.5-9b-r1-step75-vllmqwen3_8b_lang_rl_stage2_lora_r64_a32_d0.05_lr9e-6_bsz2_ga4_g8_epochs1_seed42_ddp4_vllm_07_18e5-qwen3_8b_lang_rl_stage2_lora_r64_a32_d0.05_lr9e-6_bsz2_ga4_g8_epochs6_seed42_ddp4_vllmqwen3_8b_lang_rl_lora_r64_a32_d0.05_lr9e-6_bsz2_ga4_g12_epochs1_seed42_ddp6_vllme10_qwen3_8b_lang_rl_stage2_lora_r64_a32_d0.05_lr9e-6_bsz2_ga4_g8_epochs10_seed42_ddp4_vllmtext-to-sql-shop-qwen3.5-9b-r3-step50-vllmzephyr-7b-beta-with-lora-adapters-vllm-float16-instr-lora-adapterphi-2-gpo-renew2-b0.001-vllm-merge-20k-i1phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-v2-i1vllm_finetunednx-cad-vllm-comp-8x128x21phi-2-gpo-renew2-b0.001-vllm-merge-20k-log-i1beffect_mv3_dv3_lmfcty_vllmLightOnOCR-2-1B-1025-ft-iam-lora-tiny-vllmqwen3_8b_action_rl_lora_r64_a32_d0.05_lr9e-6_bsz1_ga8_g2_epochs10_seed42_ddp4_vllm-check-570phi-2-gpo-renew2-b0.001-vllm-i1phi-2-gpo-renew2-b0.001-vllm-merge-20k-simpletest-i1phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-i1buan_6343_hw4_vLLM_classifier_headLightOnOCR-2-1B-1025-ft-iam-handwriting-vllmphi-2-gpo-renew2-b0.001-vllm-merge-20k-simpletest2-i1phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-refSFT-i1Mistral-7B-Instruct-v0.2-conllpp-turbo-lora-vllmlfm25-local-harness-rlvr-http-vllm-lora-browsecomp-20260619-baselfm25-local-harness-rlvr-http-vllm-lora-browsecomp-jsonsft-v1