config.json

{
  "_name_or_path": "rank_lstm_full_trained_depth3_n2",
  "activation_function": "silu",
  "architectures": [
    "JetMoEForCausalLM"
  ],
  "bias": true,
  "bias_mem": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "ffn_hidden_size": 5632,
  "glu": true,
  "hidden_size": 2048,
  "initializer_range": 0.01,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 4096,
  "model_type": "jetmoe",
  "moe_num_experts": 8,
  "moe_top_k": 2,
  "n_positions": 4096,
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 16,
  "num_layers": 24,
  "pad_token_id": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "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"
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "rotary_percent": 1.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.0",
  "use_cache": true,
  "vocab_size": 32000
}