Files
Qwen3-0.6B-Micro-5M/config.json
ModelHub XC 6d279575db 初始化项目,由ModelHub XC社区提供模型
Model: admijgjtjtjtjjg/Qwen3-0.6B-Micro-5M
Source: Original Platform
2026-05-07 15:59:58 +08:00

45 lines
936 B
JSON

{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 16,
"initializer_range": 0.02,
"intermediate_size": 64,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 512,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 4,
"num_hidden_layers": 4,
"num_key_value_heads": 2,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_section": [
4,
4,
8
],
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 248320
}