Astral-14B

Astral 14B is the largest model in the Astral family. It was fine-tuned from Qwen3 14b on LucidityAI/Astral-Post-Training-Dataset.

As with usual Qwen3 models, reasoning can be toggled through the usage of /no_think or not.

Example Prompt (ChatML Format (THINKING)):

<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>

Example Prompt (ChatML Format (NON-THINKING)):

<|im_start|>user
What is the capital of France? /no_think
<|im_end|>
<|im_start|>assistant
<think>
Downloads last month
23
Safetensors
Model size
14.8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LucidityAI/Astral-14B

Finetuned
Qwen/Qwen3-14B
Finetuned
(125)
this model
Quantizations
2 models

Dataset used to train LucidityAI/Astral-14B

Collection including LucidityAI/Astral-14B