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.
metricx-24-hybrid-xxl-v2p6-bfloat16ci-random-bfloat16-llama3-3bmetricx-24-hybrid-large-v2p6-bfloat16metricx-24-hybrid-xl-v2p6-bfloat16qwen3_4b_grids15_sft139-transformers-bfloat16-v1OmniVoice-bfloat16pantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-32_lr-0.0002-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0005-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-16_lr-0.0007-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-16_lr-0.0005-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-16_lr-0.0006-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0006-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-32_lr-0.0007-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-128_lr-0.0006-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-16_lr-0.0002-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-128_lr-0.0007-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-32_lr-0.0005-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-128_lr-0.0005-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-32_lr-0.0006-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0007-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-64_lr-0.0007-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-64_lr-0.0006-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-64_lr-0.0005-ggufsapiens-normal-2b-bfloat16pantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-128_lr-0.0002-ggufuio2-xxl-bfloat16pantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-64_lr-0.0002-ggufpantelis-ninja_-_unsloth-Qwen2.5-3B-Instruct_dtype-bfloat16_r-8_lr-0.0002-ggufsapiens-seg-0.3b-bfloat16uio2-large-bfloat16
