MedSLM / config.json
Saminx22's picture
Upload MedSLM: model weights, optimizer, tokenizer, config, and model card
10e3fe8 verified
{
"block_size": 1024,
"vocab_size": 50257,
"n_layer": 24,
"n_head": 16,
"n_kv_head": 8,
"n_embd": 1024,
"dropout": 0.1,
"rope_theta": 10000.0,
"architecture": "MedSLM",
"model_type": "med-slm",
"improvements": [
"RMSNorm (replaces LayerNorm)",
"Rotary Positional Embeddings / RoPE (replaces learned absolute)",
"SwiGLU activation (replaces GELU)",
"Grouped-Query Attention / GQA (replaces standard MHA)"
]
}