config.json

{
  "architectures": [
    "MixtralForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "DiscoResearch/mixtral-7b-8expert--configuration_moe_mistral.MixtralConfig",
    "AutoModelForCausalLM": "DiscoResearch/mixtral-7b-8expert--modeling_moe_mistral.MixtralForCausalLM"
  },
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_experts": 8,
  "num_experts_per_token": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.36.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}