|
{ |
|
"_name_or_path": "tiiuae/falcon-7b", |
|
"alibi": false, |
|
"apply_residual_connection_post_layernorm": false, |
|
"architectures": [ |
|
"FalconForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig", |
|
"AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel", |
|
"AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification", |
|
"AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification", |
|
"AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering", |
|
"AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM" |
|
}, |
|
"bias": "none", |
|
"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, |
|
"parallel_attn": true, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.30.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 65024, |
|
"fan_in_fan_out": false, |
|
"inference_mode": true, |
|
"init_lora_weights": true, |
|
"layers_pattern": null, |
|
"layers_to_transform": null, |
|
"lora_alpha": 16, |
|
"lora_dropout": 0.1, |
|
"modules_to_save": null, |
|
"peft_type": "LORA", |
|
"r": 64, |
|
"revision": null, |
|
"target_modules": [ |
|
"query_key_value", |
|
"dense", |
|
"dense_h_to_4h", |
|
"dense_4h_to_h" |
|
], |
|
"task_type": "CAUSAL_LM" |
|
} |