config.json

{
  "_name_or_path": "/monster/data/model/dbrx-base-converted-v2/",
  "architectures": [
    "DbrxForCausalLM"
  ],
  "attn_config": {
    "clip_qkv": 8,
    "kv_n_heads": 8,
    "model_type": "",
    "rope_theta": 500000
  },
  "auto_map": {
    "AutoConfig": "configuration_dbrx.DbrxConfig",
    "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
  },
  "d_model": 6144,
  "emb_pdrop": 0.0,
  "ffn_config": {
    "ffn_hidden_size": 10752,
    "model_type": "",
    "moe_jitter_eps": 0.01,
    "moe_loss_weight": 0.05,
    "moe_num_experts": 16,
    "moe_top_k": 4
  },
  "initializer_range": 0.02,
  "max_seq_len": 32768,
  "model_type": "dbrx",
  "n_heads": 48,
  "n_layers": 40,
  "output_router_logits": false,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.005,
    "desc_act": false,
    "group_size": 128,
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "resid_pdrop": 0.0,
  "router_aux_loss_coef": 0.05,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.38.2",
  "use_cache": true,
  "vocab_size": 100352
}