Files
malaysian-mistral-474M-4096/config.json
ModelHub XC b64e631001 初始化项目,由ModelHub XC社区提供模型
Model: mesolitica/malaysian-mistral-474M-4096
Source: Original Platform
2026-05-07 14:13:05 +08:00

27 lines
647 B
JSON

{
"_name_or_path": "pretrain-mistral-474M/checkpoint-58400",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 16,
"num_hidden_layers": 26,
"num_key_value_heads": 8,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 32000
}