26 lines
668 B
JSON
26 lines
668 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 12288,
|
||
|
|
"max_position_embeddings": 40960,
|
||
|
|
"model_type": "qwen3",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 36,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 151643,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"unsloth_version": "2026.3.4",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|