{
  "_name_or_path": "lemon07r/Gemma-2-Ataraxy-v4d-9B",
  "architectures": [
    "MixtralForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": 50.0,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "eos_token_id": 1,
  "final_logit_softcapping": 30.0,
  "head_dim": 256,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "model_type": "mixtral",
  "num_attention_heads": 16,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 42,
  "num_key_value_heads": 8,
  "num_local_experts": 2,
  "output_router_logits": false,
  "pad_token_id": 0,
  "query_pre_attn_scalar": 224,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "sliding_window": null,
  "sliding_window_size": 4096,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 256000
}