config.json

{
  "model_type": "nanochat",
  "architecture": "gpt",
  "n_layer": 20,
  "n_head": 10,
  "n_kv_head": 10,
  "n_embd": 1280,
  "vocab_size": 65536,
  "sequence_len": 2048,
  "phase": "sft",
  "checkpoint_step": 000700,
  "torch_dtype": "bfloat16"
}