{ | |
"activation_function": "gelu_new", | |
"architectures": [ | |
"GPT2LMHeadModel" | |
], | |
"attn_pdrop": 0.1, | |
"bos_token_id": 50256, | |
"embd_pdrop": 0.1, | |
"eos_token_id": 50256, | |
"initializer_range": 0.02, | |
"layer_norm_epsilon": 1e-05, | |
"model_type": "gpt2", | |
"n_ctx": 1024, | |
"n_embd": 1024, | |
"n_head": 16, | |
"n_layer": 24, | |
"n_positions": 1024, | |
"n_special": 0, | |
"predict_special_tokens": true, | |
"resid_pdrop": 0.1, | |
"summary_activation": null, | |
"summary_first_dropout": 0.1, | |
"summary_proj_to_labels": true, | |
"summary_type": "cls_index", | |
"summary_use_proj": true, | |
"task_specific_params": { | |
"text-generation": { | |
"do_sample": true, | |
"max_length": 50 | |
} | |
}, | |
"vocab_size": 50257, | |
"quantization_config": { | |
"quant_method": "exl2", | |
"version": "0.1.5", | |
"bits": 2.5, | |
"head_bits": 6, | |
"calibration": { | |
"rows": 100, | |
"length": 1024, | |
"dataset": "(default)" | |
} | |
} | |
} |