{ | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 4096, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 16384, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 48, | |
"num_key_value_heads": 4, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": null, | |
"rope_theta": 5000000, | |
"tie_word_embeddings": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.40.0", | |
"use_cache": false, | |
"vocab_size": 64000, | |
"quantization_config": { | |
"quant_method": "exl2", | |
"version": "0.0.21", | |
"bits": 6.0, | |
"head_bits": 8, | |
"calibration": { | |
"rows": 100, | |
"length": 2048, | |
"dataset": "(default)" | |
} | |
} | |
} |