전체 검색
AI 모델 84761
- paligemma2-3b-mix-224↗
Google
- parakeet-ctc-1.1b-gguf↗
handy-computer
Ported from upstream commit a707e81, pinned 2026-05-10. Validated against the NeMo reference at transcribe.cpp commit 42528dd on 2026-05-10. Offline English speech-to-text with greedy CTC decoding. A FastConformer-XL encoder with a linear CTC head. Output is lowercase, no punctuation. Not a streaming model and does not translate. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
- chat↗
harpertoken
- Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp↗
invalid-coder
NeuralPipe-7B-slerp is a merge of the following models using LazyMergekit: * jeonsworld/CarbonVillain-en-10.7B-v2 * kyujinpy/Sakura-SOLAR-Instruct
- prefect-illustrious-xl-v3-sdxl↗
John6666
Original model is here. This model created by Goofy_Ai.
- kotoba-whisper-v2.0-mlx↗
kaiinui
- kanana-2-30b-a3b-instruct↗
kakaocorp
- Gemma-4-31B-it-ROCmFP4-GGUF↗
kingjones777
- EXAONE-4.5-33B↗
LGAI-EXAONE
We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality. EXAONE 4.5 features 33 billion parameters in total, including 1.2 billion parameters from the vision encoder. EXAONE 4.5 achieves competitive performance in general benchmark while outperforming SOTA models of similar size in document understanding and Korean contextual reasoning, inheriting powerful language capabilities from our previous language models. For more details, please refer to the technical report, blog and GitHub. - Model Type: Causal Language Model + Vision Encoder - Number of Parameters (Language Model): 31.7B - Number of Parameters (Vision Encoder): 1.29B - Hidden Dimension: 5,120 - Intermediate size: 27,392 - Number of Layers: 64 Main layers + 1 MTP layers - Hybrid Attention Pattern: 16 x (3 Sliding window attention + 1 Global attention) - Reordered Norm: Apply normalization after Attention/MLP, and before residual connection - Sliding Window Attention - Number of Attention Heads: 40 Q-heads and 8 KV-heads - Head Dimension: 128 for both Q/KV - Sliding Window Size: 4096 - Global Attention - Number of Attention Heads: 40 Q-heads and 8 KV-heads - Head Dimension: 128 for both Q/KV - No Rotary Positional Embedding Used (NoPE) - Vision Encoder - Grouped Query Attention (GQA) - 2D RoPE for vision embeddings - Vocab Size: 153,600 - Context Length: 262,144 tokens - Knowledge Cutoff: Dec 2024 (2024/12)
- LFM3-Omni-2B-MLX-bf16↗
LiquidAI
