llama-13b-accelerator / config.json
Joshua Rosenkranz
initial commit of speculator weights
7a02f91
raw
history blame
318 Bytes
{
"architectures": [
"MLPSpeculatorPreTrainedModel"
],
"emb_dim": 5120,
"inner_dim": 4096,
"model_type": "mlp_speculator",
"n_candidates": 5,
"n_predict": 3,
"top_k_tokens_per_head": [
5,
3,
2
],
"torch_dtype": "float16",
"transformers_version": "4.35.0",
"vocab_size": 32000
}