config.json

{
  "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsuqtzil_0kg7ebota",
  "architectures": [
    "MambaForCausalLM"
  ],
  "bos_token_id": 0,
  "conv_kernel": 4,
  "eos_token_id": 0,
  "expand": 2,
  "fused_add_norm": true,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.1,
  "intermediate_size": 8192,
  "layer_norm_epsilon": 1e-05,
  "model_type": "mamba",
  "n_layer": 64,
  "num_hidden_layers": 64,
  "pad_token_id": 0,
  "pad_vocab_size_multiple": 8,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "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": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rescale_prenorm_residual": false,
  "residual_in_fp32": true,
  "rms_norm": true,
  "state_size": 16,
  "time_step_floor": 0.0001,
  "time_step_init_scheme": "random",
  "time_step_max": 0.1,
  "time_step_min": 0.001,
  "time_step_rank": 256,
  "time_step_scale": 1.0,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0",
  "use_bias": false,
  "use_cache": true,
  "use_conv_bias": true,
  "vocab_size": 50432
}