Miau Labs / Insight
Inkling: Our Open-Weights Model
Thinking Machines Lab has released Inkling, an open-weights model with multimodal capabilities. The model has 975B total parameters and 41B active parameters, and is trained on 45 trillion tokens of text, images, audio, and video. Inkling is licensed under Apache-2.0 and is intended as a strong base model for fine-tuni
Thinking Machines Lab has released Inkling, an open-weights model with multimodal capabilities. The model has 975B total parameters and 41B active parameters, and is trained on 45 trillion tokens of text, images, audio, and video. Inkling is licensed under Apache-2.0 and is intended as a strong base model for fine-tuning using the Tinker training platform. Inkling is a good option for fine-tuning using the Tinker platform due to its strong base model capabilities and multimodal features.
Thinking Machines Lab has released Inkling, an open-weights model with multimodal capabilities. The model has 975B total parameters and 41B active parameters, and is trained on 45 trillion tokens of text, images, audio, and video. Inkling is licensed under Apache-2.0 and is intended as a strong base model for fine-tuni
- Thinking Machines Lab has released Inkling, an open-weights model with 975B total parameters and 41B active parameters.
- Inkling is a multimodal model trained on 45 trillion tokens of text, images, audio, and video.
- The model is licensed under Apache-2.0 and is intended as a strong base model for fine-tuning using the Tinker training platform.
Miau Labs takeInkling is a good option for fine-tuning using the Tinker platform due to its strong base model capabilities and multimodal features.