|
{ |
|
"_name_or_path": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", |
|
"activation_function": "silu", |
|
"architectures": [ |
|
"ExaoneForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--configuration_exaone.ExaoneConfig", |
|
"AutoModelForCausalLM": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--modeling_exaone.ExaoneForCausalLM", |
|
"AutoModelForSequenceClassification": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--modeling_exaone.ExaoneForSequenceClassification" |
|
}, |
|
"bos_token_id": 1, |
|
"embed_dropout": 0.0, |
|
"eos_token_id": 361, |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_position_embeddings": 4096, |
|
"model_type": "exaone", |
|
"num_attention_heads": 32, |
|
"num_key_value_heads": 8, |
|
"num_layers": 32, |
|
"pad_token_id": 0, |
|
"rope_scaling": null, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.46.2", |
|
"use_cache": true, |
|
"vocab_size": 102400 |
|
} |
|
|