INTERS-Falcon-1b / config.json
yutaozhu94's picture
Upload config.json with huggingface_hub
604307f verified
raw
history blame
1.22 kB
{
"_name_or_path": "/fs/archive/share/u20238046/falcon-rw-1b",
"alibi": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_falcon.FalconConfig",
"AutoModel": "modeling_falcon.FalconModel",
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
},
"bias": true,
"bos_token_id": 1,
"eos_token_id": 2,
"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": "4.36.2",
"use_cache": true,
"vocab_size": 50304
}