lyraChatGLM / models /config.ini
vanewu's picture
NewAcceleration (#19)
78728a3
raw
history blame
243 Bytes
[glm6b]
model_name = chatglm-6b
head_num = 32
size_per_head = 128
inter_size = 16384
max_pos_seq_len = 2048
num_layer = 28
vocab_size = 130528
start_id = 130004
end_id = 130005
weight_data_type = fp16
tensor_para_size = 1
layernorm_eps = 1e-5