{ "architectures": [ "NanoChatGPT" ], "model_type": "nanochat-gpt", "vocab_size": 65536, "n_layer": 20, "n_head": 10, "n_kv_head": 10, "n_embd": 1280, "sequence_len": 2048, "torch_dtype": "bfloat16", "transformers_version": "custom", "nanochat_source": "mid", "nanochat_training_step": 808, "nanochat_val_bpb": 0.3951428487291989 }