Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

无法从 HF #280 转换羊驼重量 #72

Open
ziwang-com opened this issue Jun 5, 2023 · 0 comments
Open

无法从 HF #280 转换羊驼重量 #72

ziwang-com opened this issue Jun 5, 2023 · 0 comments

Comments

@ziwang-com
Copy link
Owner

Lightning-AI/lit-llama#280

羊驼版本是在嵌入层中添加了一个额外的令牌来训练的,这就是转换失败的原因。一般来说,如果有一个骆驼模型具有不同的权重/词汇大小等配置,则转换为我们的“7B”定义是行不通的,我们不应该期望它。

您可以尝试通过删除转换脚本中的最后一行来截断嵌入层:

点亮骆驼/脚本/convert_hf_checkpoint.py

第 89 行 in5df20分贝

如果名称中的“模型.layers”:
通过添加条件:

if "embed_tokens" in name:
sd[weight_map[name]] = param[:32000]
(伪代码)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant