KUTE-Mini / config.json
Axon-A1's picture
Upload config.json with huggingface_hub
dade801 verified
Raw History Blame Contribute Delete
282 Bytes
{
"model": "KUTE-Mini",
"dataset": "OpenLLM-Ro/fineweb2-ro-llm",
"from_scratch": true,
"vocab_size": 16000,
"d_model": 256,
"n_heads": 8,
"n_layers": 6,
"d_ff": 1024,
"max_seq_len": 128,
"parameters": 8867840,
"global_step": 5000,
"loss": 3.936351478099823
}