サイト内検索
AI モデル 85012
- rubert-large-uncased-sts↗
sergeyzh
- flan-t5-base_glue-rte↗
tanganke
- Camel-Platypus2-70B-GGUF↗
TheBloke
- Karen_TheEditor_V2_STRICT_Mistral_7B-GGUF↗
TheBloke
- Synatra-V0.1-7B-Instruct-GGUF↗
TheBloke
- convnext_tiny.in12k_ft_in1k_384↗
timm
A ConvNeXt image classification model. Pretrained in `timm` on ImageNet-12k (a 11821 class subset of full ImageNet-22k) and fine-tuned on ImageNet-1k by Ross Wightman.
- Vemana-Base-GGUF↗
udgamlabs
- gatortron-base↗
UFNLP
Developed by a joint effort between the University of Florida and NVIDIA, GatorTron-Base is a clinical language model of 345 million parameters, pre-trained using a BERT architecure implemented in the Megatron package (https://github.com/NVIDIA/Megatron-LM). This model is converted to Hugginface from : https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og Model | Parameter | Maximum input --- | --- | --- gatortron-base-2k | 345 million | 2048 gatortron-base (this model) | 345 million | 512 gatortronS | 345 million | 512 gatortron-medium | 3.9 billion | 512 gatortron-large | 8.9 billion | 512
- Qwen3.5-397B-A17B-GGUF↗
unsloth
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. Disable thinking via `--chat-template-kwargs '{"enable_thinking":false}'`. Read our guide. - All GGUFs now use our new imatrix data. See some improvements in chat, coding, long context, and tool-calling use-cases. - GGUFs now updated with an improved quantization algorithm. - See our new benchmarks for Qwen3.5 here. ---
- Ming-Image-0.1-Design-GGUF↗
voltaire321
