| { | |
| "architectures": [ | |
| "HyperCLOVAXForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_multiplier": 0.0078125, | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig", | |
| "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel", | |
| "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM" | |
| }, | |
| "bos_token_id": 100257, | |
| "deepconf_disable": false, | |
| "deepconf_enable": null, | |
| "deepconf_threshold": -3.5, | |
| "deepconf_top_r": 5, | |
| "deepconf_warmup_tokens": 0, | |
| "deepconf_window": 512, | |
| "embd_pdrop": 0.0, | |
| "embedding_multiplier": 10.0, | |
| "end_token_id": 100257, | |
| "eos_token_id": 100257, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.012727922061357854, | |
| "intermediate_size": 14336, | |
| "logits_scaling": 0.125, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "hyperclovax", | |
| "num_attention_heads": 48, | |
| "num_hidden_layers": 38, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 100257, | |
| "pretraining_tp": 1, | |
| "resid_pdrop": 0.0, | |
| "residual_multiplier": 1.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 100000000, | |
| "summary_first_dropout": 0.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.4", | |
| "use_cache": false, | |
| "use_post_norm": true, | |
| "vocab_size": 110592 | |
| } | |