llama-2-7b-chat-hf 参数及size

最新推荐文章于 2025-01-22 18:25:06 发布

长腿老头o3o

最新推荐文章于 2025-01-22 18:25:06 发布

阅读量1.4k

点赞数 3

分类专栏：学习记录文章标签：语言模型 llama

本文链接：https://blog.csdn.net/qq_61631811/article/details/137959416

版权

「学习记录」

模型结构：

LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 2048,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.38.2",
  "use_cache": true,
  "vocab_size": 32000
}

重要的：32层，32个attention hea