config.json

{
  "architectures": [
    "NanoChatForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_nanochat.NanoChatConfig",
    "AutoModelForCausalLM": "modeling_nanochat.NanoChatForCausalLM"
  },
  "model_type": "nanochat",
  "vocab_size": 65536,
  "n_positions": 2048,
  "n_embd": 1280,
  "n_layer": 20,
  "n_head": 10,
  "n_kv_head": 10,
  "n_inner": 5120,
  "activation_function": "relu_squared",
  "resid_pdrop": 0.0,
  "embd_pdrop": 0.0,
  "attn_pdrop": 0.0,
  "layer_norm_epsilon": 1e-5,
  "hidden_size": 1280,
  "num_hidden_layers": 20,
  "num_attention_heads": 10,
  "num_key_value_heads": 10,
  "intermediate_size": 5120,
  "hidden_act": "relu2",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "resid_dropout": 0.0,
  "emb_dropout": 0.0,
  "layer_norm_eps": 1e-6,
  "initializer_range": 0.02,
  "max_position_embeddings": 2048,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "pad_token_id": 0,
  "tie_word_embeddings": false,
  "softcap": 15.0,
  "logits_soft_cap": 15.0,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "dtype": "bfloat16",
  "torch_dtype": "bfloat16",
  "transformers_version": "5.0.0.dev0",
  "use_cache": true
}