01-ai/Yi-1.5-9B/bert4torch_config.json

{
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 48,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "layer_norm_eps": 1e-06,
  "rope_theta": 5000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "vocab_size": 64000,
  "skip_init": true,
  "rope_rank": "updown",
  "segment_vocab_size": 0,
  "generation_config": {"tokenizer_decode_config": {"skip_special_tokens": true}, "max_length": 4096, "eos_token_id": 2}
}