config.json

{
    "architectures": [
      "MistralForCausalLM"
    ],
    "bos_token_id": 1,
    "c_max_position_embeddings": 4096,
    "eos_token_id": 2,
    "flash_attn_key_chunk_size": 1024,
    "flash_attn_query_chunk_size": 1024,
    "freq_max_position_embeddings": 32768,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 4096,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "number_rep_kv": 1,
    "pad_token_id": 2,
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000.0,
    "scan_mlp_chunk_size": 1024,
    "sliding_window": 4096,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.35.0.dev0",
    "use_cache": true,
    "use_flash_attention": false,
    "use_pjit_attention_force": true,
    "use_sacn_mlp": false,
    "vocab_size": 32000
  }