サイト内検索

AI モデル 85003

• pixal3d-q8_0-v1↗

  raven38

  GGUF weights for `pixal3d.cpp`, a GGML-based C++ image→3D pipeline. This is the **Web release set**: Q8_0 quantization, 9 files, 7.54 GiB, sized so that Texture Flow fits the browser WebGPU per-buffer budget (measured peak 2,517 MB against 4,095 MB, 38 % headroom). The repository layout is flat and the file names are exact, because the consuming client verifies every file's `size_bytes` and SHA-256 against the committed manifest `pixal3d-models.json` before the set is marked usable. or pass `--model-base-url` with `--model-manifest` to the desktop installer. The client streams each file into origin-owned storage and refuses the set unless every file matches the manifest exactly.

• flammenai_-_flammen-mistral-7B-gguf↗

  RichardErkhov

• lemon-mint_-_gemma-ko-7b-instruct-v0.71-gguf↗

  RichardErkhov

• mylesgoose_-_Llama-3.2-1B-Instruct-abliterated3-gguf↗

  RichardErkhov

• sam-paech_-_qwen-2.5-32b-instruct-resized-gguf↗

  RichardErkhov

• MiniMax-H3↗

  Rin247

• acoustic-acestep1.5-v1↗

  ryanontheinside

• absolute-harmfulness-predictor-redteam↗

  safepaca

  This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1197 - Mse: 1.1197 The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - num_epochs: 1.0

• Lily-Cybersecurity-7B-v0.2↗

  segolilylabs

• Qwen3.8-9B-mlx-8Bit↗

  SiddhJagani