|
{ |
|
"_name_or_path": "tiiuae/falcon-11B", |
|
"activation": "gelu", |
|
"alibi": false, |
|
"architectures": [ |
|
"FalconForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig", |
|
"AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel", |
|
"AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM", |
|
"AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering", |
|
"AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification", |
|
"AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification" |
|
}, |
|
"bias": false, |
|
"bos_token_id": 11, |
|
"eos_token_id": 11, |
|
"ff_factor": 4, |
|
"ffn_hidden_size": 16384, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_position_embeddings": 8192, |
|
"model_type": "falcon", |
|
"multi_query": true, |
|
"new_decoder_architecture": true, |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 60, |
|
"num_kv_heads": 8, |
|
"num_ln_in_parallel_attn": 1, |
|
"parallel_attn": true, |
|
"rope_scaling": null, |
|
"rope_theta": 500042.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.39.2", |
|
"use_cache": true, |
|
"vocab_size": 65024 |
|
} |
|
|