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.
Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float16PREMOVE_gpt-oss-120b_float16Meta-Llama-3.2-8B-Instruct-ct2-int8_float16calm2-7b-chat-dpo-experimental-float16Llama3-Toxic-8B-Float16Meta-Llama-3-8B-Instruct-ct2-int8_float16Comb_llama3.1-8b-Instruct_5e-2_float16gemma3-1b-sft-kannada-general-float16gemma3-1b-sft-kannada-physics-float16PREMOVE_qwen3-32b_float16Weighted_llama3.1-8b-Instruct_5e-2_float16M1NDB0T-0M3G4-29B_FLOAT16gemma3-1b-sft-sitcom-office-reasoning-float16PREMOVE_gpt-oss-20b_float16open-llama-7b-open-instruct-ct2-float16llama3.1_float16llama-3-personal-finance-8b-bnb-4bit-float16mistral_nemo_12b_reasoning_psychology_float16llama3.1-8b-instruct-summarize-float16float16dipg-safety-agent-v2-float16llama-3.1-8b-CoT-N100-float16-vllmMeta-Llama-3.1-8B-Instruct-ct2-int8_float16vaidya_midnight_Pure_float16_vllmLlama3.1_GRPO_float16phi-4-sft-sitcom-office-float16gpt-oss-20b-finetune-arg-v01-vllm-float16qwen-8b-finetune-dave-v03-vllm-float16open-llama-13b-open-instruct-ct2-int8_float16gemma-3-1b-it-unsloth-bnb-4bit-float16