Files
ModelHub XC 8653d43e44 初始化项目,由ModelHub XC社区提供模型
Model: saidutta69/Qwen2.5-7B-Instruct-1M-heretic
Source: Original Platform
2026-09-16 21:55:29 +08:00

67 lines
1.5 KiB
JSON

{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"dual_chunk_attention_config": {
"chunk_size": 262144,
"local_size": 8192,
"original_max_position_embeddings": 262144
},
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"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"
],
"max_position_embeddings": 1010000,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": null,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.14.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}