config.json

{
  "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig",
    "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel",
    "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM",
    "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering",
    "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification",
    "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification"
  },
  "bias": false,
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_size": 4544,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "falcon",
  "multi_query": true,
  "new_decoder_architecture": false,
  "num_attention_heads": 71,
  "num_hidden_layers": 32,
  "num_kv_heads": 71,
  "parallel_attn": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.30.2",
  "use_cache": true,
  "vocab_size": 65024
}