33 lines
770 B
JSON
33 lines
770 B
JSON
{
|
|
"architectures": [
|
|
"SeedOssForCausalLM"
|
|
],
|
|
"attention_bias": true,
|
|
"attention_dropout": 0.1,
|
|
"attention_out_bias": false,
|
|
"bos_token_id": 0,
|
|
"pad_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 27648,
|
|
"max_position_embeddings": 524288,
|
|
"mlp_bias": false,
|
|
"model_type": "seed_oss",
|
|
"num_attention_heads": 80,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"residual_dropout": 0.1,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": {
|
|
"rope_type": "default"
|
|
},
|
|
"rope_theta": 10000000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.55.0",
|
|
"use_cache": true,
|
|
"vocab_size": 155136
|
|
} |