Files
K2S3-Mistral-7bx2-48layers_…/config.json
ModelHub XC 7a16565e5d 初始化项目,由ModelHub XC社区提供模型
Model: Changgil/K2S3-Mistral-7bx2-48layers_v1.2
Source: Original Platform
2026-05-20 03:49:27 +08:00

27 lines
670 B
JSON

{
"_name_or_path": "/home/cgsong/mergekit/mistral_7bx2_48layers_v1.2",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.38.0.dev0",
"use_cache": false,
"vocab_size": 48000
}