testv332 / config.json
C10X's picture
Upload 6 files
a0b00a9 verified
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 2048,
"layer_types": [
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 8192,
"max_window_layers": 5,
"model_type": "qwen3",
"num_attention_heads": 8,
"num_hidden_layers": 6,
"num_key_value_heads": 2,
"pad_token_id": 2,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 500000,
"rope_type": "default"
},
"sliding_window": 512,
"tie_word_embeddings": true,
"transformers_version": "5.8.0.dev0",
"use_cache": false,
"use_sliding_window": true,
"vocab_size": 16384
}