31 lines
711 B
JSON
31 lines
711 B
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 3,
|
|
"eos_token_id": 5,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 576,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 1536,
|
|
"max_position_embeddings": 4096,
|
|
"max_window_layers": 30,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 9,
|
|
"num_hidden_layers": 30,
|
|
"num_key_value_heads": 3,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 100000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.51.0",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 64000
|
|
}
|