llm-course-hw1 / config.json
EgorKim's picture
Push model using huggingface_hub.
66e339f verified
raw
history blame contribute delete
162 Bytes
{
"dropout": 0.1,
"hidden_dim": 384,
"intermediate_dim": 1024,
"max_seq_len": 128,
"n_head": 6,
"n_kv_head": 3,
"n_layer": 6,
"vocab_size": 1024
}