6 Star 59 Fork 17

Shenzhi Wang / Llama3-70B-Chinese-Chat

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
克隆/下载
config.json 648 Bytes
一键复制 编辑 原始数据 按行查看 历史
Shenzhi Wang 提交于 2024-05-10 12:16 . 更新 config.json
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 128256
}
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/shenzhi-wang/llama3-70b-chinese-chat.git
git@gitee.com:shenzhi-wang/llama3-70b-chinese-chat.git
shenzhi-wang
llama3-70b-chinese-chat
Llama3-70B-Chinese-Chat
master

搜索帮助

344bd9b3 5694891 D2dac590 5694891