config.json

{
  "architectures": [
    "SSLLMForCausalLM"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 100256,
  "d_ff": 2560,
  "d_model": 768,
  "dropout_rate": 0.1,
  "eos_token_id": 100257,
  "hidden_size": 768,
  "intermediate_size": 2560,
  "max_position_embeddings": 1024,
  "max_seq_len": 1024,
  "model_type": "ssllm",
  "num_attention_heads": 12,
  "num_heads": 12,
  "num_hidden_layers": 10,
  "num_layers": 10,
  "pad_token_id": 100257,
  "stochastic_depth_rate": 0.1,
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "vocab_size": 100277
}