config.json

{
  "RoPE": {
    "last_k_rope_dim": 0,
    "n_gqa_group": 3,
    "partial_rope_version": 4,
    "qk_tensor_path": "/home/binguo/data/MLA-FT/utils/qk_tensor_135M.pth",
    "top_k_rope_dim": 4,
    "uniform_start_point": 0,
    "uniform_step": 1
  },
  "SVD": {
    "low_rank": 8,
    "method": 7
  },
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 576,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 9,
  "num_hidden_layers": 30,
  "num_key_value_heads": 3,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 49152
}