config.json

{
  "_name_or_path": "badochov-epfl/oelm_llama",
  "activation_fn_name": "swish",
  "architectures": [
    "OpenELMForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "apple/OpenELM-270M-Instruct--configuration_openelm.OpenELMConfig",
    "AutoModelForCausalLM": "apple/OpenELM-270M-Instruct--modeling_openelm.OpenELMForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "ffn_dim_divisor": 256,
  "ffn_multipliers": [
    0.5,
    0.73,
    0.97,
    1.2,
    1.43,
    1.67,
    1.9,
    2.13,
    2.37,
    2.6,
    2.83,
    3.07,
    3.3,
    3.53,
    3.77,
    4.0
  ],
  "ffn_with_glu": true,
  "head_dim": 64,
  "initializer_range": 0.02,
  "max_context_length": 2048,
  "model_dim": 1280,
  "model_type": "openelm",
  "normalization_layer_name": "rms_norm",
  "normalize_qk_projections": true,
  "num_gqa_groups": 4,
  "num_kv_heads": [
    3,
    3,
    3,
    3,
    3,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    5,
    5,
    5,
    5
  ],
  "num_query_heads": [
    12,
    12,
    12,
    12,
    12,
    16,
    16,
    16,
    16,
    16,
    16,
    16,
    20,
    20,
    20,
    20
  ],
  "num_transformer_layers": 16,
  "qkv_multipliers": [
    0.5,
    1.0
  ],
  "rope_freq_constant": 10000,
  "rope_max_length": 4096,
  "share_input_output_layers": true,
  "torch_dtype": "float32",
  "transformers_version": "4.40.2",
  "use_cache": true,
  "vocab_size": 32000
}