Files
matritest_600M/config.json
ModelHub XC 4ebce319fc 初始化项目,由ModelHub XC社区提供模型
Model: nthngdy/matritest_600M
Source: Original Platform
2026-09-10 12:12:17 +08:00

32 lines
739 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "float32",
"eos_token_id": 0,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1792,
"initializer_range": 0.041666666666666664,
"intermediate_size": 7168,
"is_llama_config": true,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 28,
"num_hidden_layers": 5,
"num_key_value_heads": 28,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_interleaved": false,
"rope_scaling": null,
"rope_theta": 100000,
"tie_word_embeddings": false,
"transformers_version": "4.57.0",
"use_cache": true,
"vocab_size": 49152
}