[Simulator] Add high-fidelity CPU-based inference simulator (#33824)
Co-authored-by: zhouhaizhu.zhz <zhouhaizhu.zhz@alibaba-inc.com> Co-authored-by: LinSiyuan814 <linsiyuan.lsy@alibaba-inc.com> Co-authored-by: hzh0425 <hzh0425@apache.org>
This commit is contained in:
co-authored by
zhouhaizhu.zhz
LinSiyuan814
hzh0425
parent
a5f07b1241
commit
59799a3687
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": ["Qwen3ForCausalLM"],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
Reference in New Issue
Block a user