39 lines
862 B
JSON
39 lines
862 B
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"dtype": "float16",
|
|
"head_dim": 96,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 768,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2432,
|
|
"layer_types": [
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention"
|
|
],
|
|
"max_position_embeddings": 8192,
|
|
"max_window_layers": 28,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 8,
|
|
"num_hidden_layers": 8,
|
|
"num_key_value_heads": 4,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 6400
|
|
}
|