|
{ |
|
"_name_or_path": "falcon-125m", |
|
"activation": "gelu", |
|
"alibi": false, |
|
"apply_residual_connection_post_layernorm": false, |
|
"architectures": [ |
|
"FalconForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"attention_matrix_factorization_rank": 128, |
|
"auto_map": { |
|
"AutoConfig": "tiiuae/falcon-7b-instruct--configuration_falcon.FalconConfig", |
|
"AutoModel": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconModel", |
|
"AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForCausalLM", |
|
"AutoModelForQuestionAnswering": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForQuestionAnswering", |
|
"AutoModelForSequenceClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForSequenceClassification", |
|
"AutoModelForTokenClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForTokenClassification" |
|
}, |
|
"bias": false, |
|
"bos_token_id": 11, |
|
"eos_token_id": 11, |
|
"feedforward_matrix_factorization_rank": 128, |
|
"ffn_hidden_size": 18176, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "falcon", |
|
"multi_query": true, |
|
"new_decoder_architecture": false, |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 10, |
|
"num_kv_heads": 71, |
|
"num_ln_in_parallel_attn": null, |
|
"parallel_attn": true, |
|
"quantization_aware_training": true, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.44.2", |
|
"use_cache": true, |
|
"use_early_exiting": true, |
|
"use_reversible_layers": true, |
|
"vocab_size": 65024 |
|
} |
|
|