Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
19 shown of 30,614
LTXV-13B-0.9.8-Dev-Q8_0.gguf
qwen_image_fp8_hq.safetensors
PaddleOCR OpenVINO
将 PaddleOCR PP-OCRv4/v5 模型转换为 OpenVINO IR 格式(.xml + .bin)。 支持通过 PaddleOCR-OpenVINO C++ 运行时 在 Intel NPU / CPU / GPU 上进行本地推理,无需联网。
Smollm2 135m SAE
license: mit language: en basemodel: HuggingFaceTB/SmolLM2-135M tags: sae mechanistic-interpretability sparse-autoencoders monosemanticity feature-extraction smollm2 interpretability atlas pipelinetag: feature-extraction
17336
Exact lora artifact distributed with Roukin8-character-LoHa/LoCon/FullCkpt ろうきん8 (LoHa).
mova_360p_low_noise.safetensors
Qwen-Image-Q4_K_S.gguf
Wan2.2-Fun-Camera-LowNoise-14B-Q3_K_S.gguf
Visualrl LoRA M2 Only
Llama 3.2 Mavrick.Spark 1B
A fast, edge-friendly 1.23B parameter model that distills the Spark-style persona (concise, helpful, agentic vibes) and Maverick long-form reasoning traces into Meta's Llama 3.2 1B Instruct base.
Mask2former Swin Base Cubicassa
Fine-tuned version of facebook/mask2former-swin-base-coco-instance on the phungpx/cubicassa5k-coco dataset for instance segmentation of architectural floor-plan elements.
boogu_image_edit_int8_convrot.safetensors
Distilbert 8 4 1.25 85 65 75
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set: Loss: 0.3073 F1 Micro: 0.7857 F1 Macro: 0.7410 Precision Micro:...
steps_150000_pytorch_model.pt
wan2.2_bernini_r_high_noise_fp8_scaled.safetensors
gemma4_e2b_it_bf16.safetensors
Qwen-Image-Q8_0.gguf
steps_150000_pytorch_model.pt
Distilgpt2 Finetuned Wikitext2
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 3.6141
