Files
CoSineVerifier-Tool-4B/config.json
ModelHub XC fbe85120af 初始化项目,由ModelHub XC社区提供模型
Model: Nanbeige/CoSineVerifier-Tool-4B
Source: Original Platform
2026-07-25 22:18:31 +08:00

72 lines
1.6 KiB
JSON

{
"_attn_implementation_autoset": true,
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"embd_pdrop": 0.0,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.56.2",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}