config.json

{
  "_name_or_path": "tiny-random-dbrx",
  "architectures": [
    "DbrxForCausalLM"
  ],
  "attn_config": {
    "clip_qkv": 8,
    "kv_n_heads": 2,
    "model_type": "",
    "rope_theta": 500000
  },
  "d_model": 8,
  "emb_pdrop": 0.0,
  "ffn_config": {
    "ffn_hidden_size": 8,
    "model_type": "",
    "moe_jitter_eps": 0,
    "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": 4,
  "n_layers": 2,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "resid_pdrop": 0.0,
  "router_aux_loss_coef": 0.05,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "vocab_size": 100352
}