transformer-1.3B-100B / config.json
yzhangcs's picture
Upload TransformerForCausalLM
d6f66f4 verified
{
"_name_or_path": "fla-hub/transformer-1.3B-100B",
"architectures": [
"TransformerForCausalLM"
],
"attention_bias": false,
"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": 0.02,
"intermediate_size": null,
"max_position_embeddings": 2048,
"model_type": "transformer",
"norm_eps": 1e-06,
"num_heads": 32,
"num_hidden_layers": 24,
"num_kv_heads": null,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.2",
"use_cache": true,
"vocab_size": 32000,
"window_size": null
}