Files
augmented-61ee2b17ae406fc2/config.json
ModelHub XC ff9918a201 初始化项目,由ModelHub XC社区提供模型
Model: gradients-io-tournaments/augmented-61ee2b17ae406fc2
Source: Original Platform
2026-09-03 02:18:16 +08:00

60 lines
1.3 KiB
JSON

{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151643,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"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"
],
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 151646,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"unsloth_version": "2024.9",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}