| { |
| "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, |
| "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, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "group_size": 128, |
| "hyb_act": false, |
| "lm_head": false, |
| "meta": { |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:4.0.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "v2": false, |
| "v2_alpha": 0.25 |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "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": "bfloat16", |
| "transformers_version": "4.52.4", |
| "use_cache": false, |
| "use_post_norm": true, |
| "vocab_size": 110592 |
| } |
|
|
