サイト内検索

AI モデル 84759

• gte-small↗

  Supabase

  _Fork of https://huggingface.co/thenlper/gte-small with ONNX weights to be compatible with Transformers.js. See JavaScript usage._ The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including **information retrieval**, **semantic textual similarity**, **text reranking**, etc. Performance of GTE models were compared with other popular text embedding models on the MTEB benchmark. For more detailed comparison results, please refer to the MTEB leaderboard.

• py313-pylingual-v3-segmenter↗

  syssec-utd

  This model is a fine-tuned version of syssec-utd/py313-pylingual-v3-mlm on the syssec-utd/segmentation-py313-pylingual-v3-tokenized dataset. It achieves the following results on the evaluation set: - Loss: 0.0047 - Precision: 0.9945 - Recall: 0.9944 - F1: 0.9945 - Accuracy: 0.9983 The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 28 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 - mixed_precision_training: Native AMP

• tf_efficientnet_b1.ns_jft_in1k↗

  timm

  A EfficientNet image classification model. Trained on ImageNet-1k and unlabeled JFT-300m using Noisy Student semi-supervised learning in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.

• MiniCPM5-1B-Uncensored-GGUF↗

  tinyopsec

• codellama-7b-bnb-4bit↗

  unsloth

• gemma-1.1-2b-it-bnb-4bit↗

  unsloth

• Mistral-Small-3.1-24B-Instruct-2503-GGUF↗

  unsloth

  Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) **adds state-of-the-art vision understanding** and enhances **long context capabilities up to 128k tokens** without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks. This model is an instruction-finetuned version of: Mistral-Small-3.1-24B-Base-2503. Mistral Small 3.1 can be deployed locally and is exceptionally "knowledge-dense," fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized. It is ideal for: - Fast-response conversational agents. - Low-latency function calling. - Subject matter experts via fine-tuning. - Local inference for hobbyists and organizations handling sensitive data. - Programming and math reasoning. - Long document understanding. - Visual understanding.

• C2S-Pythia-410m-cell-type-prediction↗

  vandijklab

• Qwen3.8-27B-Abliterated-MLX-oQ6e-mtp↗

  windowsxp811203

• qwen3.5-9b-rp-lora-v2↗

  www622846