config.json

{
  "architectures": [
    "Plamo2ForCausalLM"
  ],
  "attention_window_size": 32768,
  "auto_map": {
    "AutoConfig": "modeling_plamo.Plamo2Config",
    "AutoModelForCausalLM": "modeling_plamo.Plamo2ForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "eval_attention_n_bit": null,
  "eval_mlp_n_bit": null,
  "fp8_accum_dtype": "bfloat16",
  "full_attention_idx": [
    0,
    2,
    4,
    6,
    8,
    10,
    12,
    14,
    16,
    18,
    20,
    22,
    24,
    26,
    28,
    30
  ],
  "hidden_size": 2048,
  "hidden_size_per_head": 128,
  "image_feature_size": null,
  "image_proj_type": "linear",
  "image_token_id": null,
  "intermediate_size": 5632,
  "linear_type": "normal",
  "mamba_chunk_size": 256,
  "mamba_d_conv": 4,
  "mamba_d_state": 64,
  "mamba_enabled": true,
  "mamba_num_heads": 64,
  "mamba_step": 2,
  "max_position_embeddings": 32768,
  "model_type": "plamo2",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "pad_token_id": 3,
  "rms_norm_eps": 0.000001,
  "rope_local_theta": 1000000.0,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tokenizer_class": "Plamo2Tokenizer",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": false,
  "vocab_size": 100000
}