These are the weights of nanochat midtrained and Supervised Finte Tuning (SFT).
You must run these weights in a GPU H100 in order to have results, otherwise it will give you an error. On the other hand you can use this repositroy that is based on the nanochat to run a notebook with the inference: https://github.com/renatocastro33/Summer_Camp_IA_PUCP_Small_Language_Model
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for renatocastro33/nanochat-d34-sft
Base model
karpathy/nanochat-d34