| { |
| "architectures": [ |
| "JiRackTernaryModel" |
| ], |
| "model_type": "jirack_ternary", |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "dtype": "bfloat16", |
| "eos_token_id": 128001, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 16384, |
| "initializer_range": 0.02, |
| "intermediate_size": 53248, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "num_attention_heads": 128, |
| "num_hidden_layers": 126, |
| "num_key_value_heads": 16, |
| "pad_token_id": null, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "quant_method": "bitnet", |
| "bits": 2, |
| "packing": "2bit_uint8", |
| "group_size": 128 |
| }, |
| "rms_norm_eps": 1e-05, |
| "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": 500000.0, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.0.0", |
| "use_cache": true, |
| "vocab_size": 128256, |
| "model_size": "405B", |
| "parameter_count": 405000000000, |
| "total_params": 405000000000 |
| } |