| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "dtype": "float16", | |
| "eos_token_id": 5, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 24576, | |
| "max_position_embeddings": 163840, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "autoround_version": "0.10.2", | |
| "bits": 3, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "iters": 300, | |
| "packing_format": "auto_round", | |
| "quant_method": "auto-round", | |
| "seqlen": 256, | |
| "sym": false | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "factor": 40.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "rope_theta": 10000.0, | |
| "rope_type": "llama3" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.3.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 256000 | |
| } | |