We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 1ae6ed8 commit 5d86da2Copy full SHA for 5d86da2
xllm/models/llm/qwen3.h
@@ -94,6 +94,7 @@ REGISTER_MODEL_ARGS(qwen3, [&] {
94
LOAD_ARG_OR(dtype, "torch_dtype", "");
95
LOAD_ARG_OR(vocab_size, "vocab_size", 152064);
96
LOAD_ARG_OR(hidden_size, "hidden_size", 3584);
97
+ LOAD_ARG_OR(hidden_act, "hidden_act", "silu");
98
LOAD_ARG_OR(n_layers, "num_hidden_layers", 28);
99
LOAD_ARG_OR(n_heads, "num_attention_heads", 28);
100
LOAD_ARG(n_kv_heads, "num_key_value_heads");
0 commit comments