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.

Sign up for GitHub

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

Jump to bottom

Garbled characters decoding on Mistral-7b-v0.1-instruct #163

Open
zengxy20 opened this issue Nov 25, 2024 · 0 comments
Open

Garbled characters decoding on Mistral-7b-v0.1-instruct #163

zengxy20 opened this issue Nov 25, 2024 · 0 comments

Comments

@zengxy20
Copy link

I have followed the sharing setting in #79 to change the cache into your customized kv_cache (MistralAttention, MistralDecoderLayer, MistralModel, MistralForCausalLM, MistralForSequenceClassification) and not used the tree_mask after causal_mask. But the outputs are garbled characters. I think there are wrong settings in our modeling_mistral_kv.py. Could you please provide me with some suggestions?
微信图片_20241123134744
微信图片_20241125185536
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@zengxy20