Files
base_PLOS-slerp_merged_mini…/config.json
ModelHub XC e5b3c4a5a0 初始化项目,由ModelHub XC社区提供模型
Model: gulsmyigit/base_PLOS-slerp_merged_ministral8b
Source: Original Platform
2026-07-25 21:46:09 +08:00

69 lines
1.6 KiB
JSON

{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 32768,
"model_type": "ministral",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 100000000.0,
"rope_type": "default"
},
"sliding_window": 32768,
"tie_word_embeddings": false,
"transformers_version": "5.12.1",
"use_cache": true,
"vocab_size": 131072
}