JRosenkranz's picture
moving model weights to ibm-granite org
1575adf
raw
history blame
332 Bytes
{
"architectures": [
"MLPSpeculatorPreTrainedModel"
],
"emb_dim": 4096,
"inner_dim": 4096,
"model_type": "mlp_speculator",
"n_candidates": 5,
"n_predict": 5,
"top_k_tokens_per_head": [
4,
3,
2,
2,
2
],
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"vocab_size": 32008
}