train/models/llama/7b_config.json

{
  "emb_size": 4096,
  "feedforward_size": 11008,
  "hidden_size": 4096,
  "hidden_act": "silu",
  "heads_num": 32,
  "layers_num": 32,
  "dropout": 0.1,
  "data_processor": "lm",
  "max_seq_length": 2048,
  "embedding": ["word"],
  "remove_transformer_bias": true,
  "remove_embedding_layernorm": true,
  "rotary_position_embedding": true,
  "encoder": "transformer",
  "feed_forward": "gated",
  "mask": "causal",
  "layernorm_positioning": "pre",
  "layernorm": "rms",
  "target": ["lm"]
}