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.
qwen3-0.6b-resume-jsonMaaza-SLM-360M-JSON-v1llama-3-8b-finance-jsonShield-Qwen3-1.7B-PEFT-CEQwen3-1.7B-ResearchReasoning-JSON-RLindian-legal-qwen2.5-1.5b-loraLLaMA2_LegalInquryBotMaaza-MLM-135M-JSON-v1Shield-Qwen3Guard-Gen-0.6B-PEFT-CEneural-scalpel-sql-json-3b-ggufQwen2.5-3B-JSON-StructuredOutputJSontologybasedcodingbotqwen3-4b-instruct-json-expert-lora-v4json-extractqwen2.5-7b-json-extraction-sftShield-Qwen3.5-0.8B-PEFT-CEqwen3-4b-sft-structured-jsonqwen3-4b-json-loraqwen-3-json-lora-v2Shield-Gemma-3-1B-PEFT-CEShield-Gemma-3-270m-PEFT-CEShield-SmolLM2-1.7B-PEFT-CEqwen2.5-3b-f1-strategy-loraqwen2.5-3b-f1-commentary-lora-v2your-lora-repoShield-Llama-3.2-1B-PEFT-CEdevstral-yaml-json-loraLlama-2-13b-hf-finetuned-SNGMistral-7B-Instruct-v0.1-JSON-Test_Generation-2-EpochDataSci-Coder-14B-LoRA