config.json

{
  "_name_or_path": "model/falcon/falcon-rw-1b-bf16-train_batch=4-train=rw_code_falcon_dataset",
  "alibi": true,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForDistill"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
  },
  "bias": true,
  "bos_token_id": 1,
  "eos_token_id": null,
  "hidden_dropout": 0.0,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "falcon",
  "multi_query": false,
  "new_decoder_architecture": false,
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_kv_heads": 32,
  "parallel_attn": false,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.34.1",
  "use_cache": true,
  "vocab_size": 50304
}