config.json

{
  "_name_or_path": "mistralai/Mistral-Large-Instruct-2407",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 12288,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "model_type": "mistral",
  "neuron": {
    "auto_cast_type": "bf16",
    "batch_size": 4,
    "checkpoint_id": "mistralai/Mistral-Large-Instruct-2407",
    "checkpoint_revision": "566a5a1fa869af019a1d937c231a76dbcb4b0d24",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.128.0+56dc5a86",
    "num_cores": 24,
    "sequence_length": 4096,
    "task": "text-generation"
  },
  "num_attention_heads": 96,
  "num_hidden_layers": 88,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.2",
  "use_cache": true,
  "vocab_size": 32768
}