Model Card for Gradience-3B

This model is still in preview/beta. We're still working on it! This is just so the community can try out our new "Gradient Reasoning" that intends to break problems down and reason faster.

You can use a system prompt to enable thinking: "First, think step-by-step to reach the solution. Enclose your entire reasoning process within <|begin_of_thought|> and <|end_of_thought|> tags." You can try sampling params: Temp: 0.76, TopP: 0.62, Topk 30-68, Rep: 1.0, minp: 0.05

Downloads last month
333
Safetensors
Model size
3.09B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Tesslate/Gradience-T1-3B-preview

Base model

Qwen/Qwen2.5-3B
Finetuned
(402)
this model
Finetunes
1 model
Quantizations
2 models

Dataset used to train Tesslate/Gradience-T1-3B-preview