Edit model card

An experimental coding instruct model. This is a full finetune of DeepSeek-Coder-Instruct-1.3B for 15 hours on 1xA6000 using a bespoke distillation trainer.

Downloads last month
6
Safetensors
Model size
1.35B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.