{
  "_name_or_path": "SmolLlamix-8x101M-take2",
  "architectures": [
    "MixtralForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 32768,
  "model_type": "mixtral",
  "num_attention_heads": 24,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 6,
  "num_key_value_heads": 8,
  "num_local_experts": 8,
  "output_router_logits": false,
  "pretraining_tp": 1,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "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": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.02,
  "router_jitter_noise": 0.0,
  "router_z_loss_coef": 0.001,
  "sliding_window": 1024,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "use_cache": false,
  "vocab_size": 32128
}