Files
Qwen2.5-7B_single_emb/config.json
ModelHub XC 0c26d2f309 初始化项目,由ModelHub XC社区提供模型
Model: ISTA-MLCV/Qwen2.5-7B_single_emb
Source: Original Platform
2026-05-25 12:25:22 +08:00

35 lines
862 B
JSON

{
"add_linear_shift": false,
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"gradual_rotation": false,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"learned_rotation": false,
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"rotation_alpha": 1.57079633,
"rotation_direction": "right",
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.51.0",
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}