config.json

{
  "_name_or_path": "data/outputs/__mistral_1__",
  "architectures": [
    "MistralForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_mistral.MistralConfig",
    "AutoModelForCausalLM": "modeling_mistral.MistralForCausalLM"
  },
  "attention_dropout": 0.0,
  "beacon_attend_prev": false,
  "beacon_attn": "step-expansion",
  "beacon_embed_init": "eos",
  "beacon_param": [
    "q",
    "k",
    "v",
    "o"
  ],
  "beacon_ratio": [
    2,
    4,
    8
  ],
  "beacon_ratio_mix": "step-random",
  "beacon_sink_size": 1,
  "beacon_stride": 2048,
  "beacon_window": 2048,
  "beacon_pos": "append",
  "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_hidden_layers": 32,
  "num_key_value_heads": 8,
  "retrieval_cache_dir": "/share/shared_models",
  "retrieval_key_length": null,
  "retrieval_method": null,
  "retrieval_topk": null,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.3",
  "use_cache": true,
  "vocab_size": 32000
}