| { | |
| "activation_function": "silu", | |
| "architectures": [ | |
| "ExaoneForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_exaone.ExaoneConfig", | |
| "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM", | |
| "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "embed_dropout": 0.0, | |
| "eos_token_id": 361, | |
| "head_dim": 128, | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27392, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 32768, | |
| "model_type": "exaone", | |
| "num_attention_heads": 40, | |
| "num_key_value_heads": 8, | |
| "num_layers": 64, | |
| "pad_token_id": 0, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 3 | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 3 | |
| }, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.43.0", | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| } |