vanilla-1.8B-4096-model / configs /transformer_1B.json
zaydzuhri's picture
Add files using upload-large-folder tool
66dbc1f verified
raw
history blame contribute delete
551 Bytes
{
"bos_token_id": 1,
"elementwise_affine": true,
"eos_token_id": 2,
"fuse_cross_entropy": true,
"fuse_norm": true,
"fuse_swiglu": true,
"hidden_act": "swish",
"hidden_ratio": 4,
"hidden_size": 2048,
"initializer_range": 0.006,
"intermediate_size": null,
"max_position_embeddings": 8192,
"model_type": "transformer",
"norm_eps": 1e-06,
"num_heads": 32,
"num_hidden_layers": 24,
"num_kv_heads": null,
"pad_token_id": 2,
"rope_theta": 10000.0,
"tie_word_embeddings": false
}