You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
----- deepseek-ai/deepseek-coder-33b-instruct -----
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
<|begin▁of▁sentence|>You are a helpful assistant### Instruction:
Hello
### Response:
Hi there
<|EOT|>
### Instruction:
Who are you
### Response:
I am an assistant
<|EOT|>
### Instruction:
Another question
### Response:
Doesn't look correct to me for deepseek-coder as the default system message ends with a newline like so:
----- deepseek-ai/deepseek-coder-33b-instruct -----
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
<|begin▁of▁sentence|>You are a helpful assistant
### Instruction:
Hello
### Response:
Hi there
<|EOT|>
### Instruction:
Who are you
### Response:
I am an assistant
<|EOT|>
### Instruction:
Another question
### Response:
Perhaps the Python script on this page should detect this and move the newline from the default system message into the template itself?
The text was updated successfully, but these errors were encountered:
Should this be VARIANTS_TO_TEST[0] and thus getting the 'teknium/OpenHermes-2.5-Mistral-7B' data or has the vector been rearranged at some time and 'google/gemma-7b-it' was originally at the start of the vector?
I noticed this when adding the 'alpaca' chat template (which is very similar to the 'deepseek-coder' chat template):
#7383 (comment)
Doesn't look correct to me for
deepseek-coder
as the default system message ends with a newline like so:Perhaps the Python script on this page should detect this and move the newline from the default system message into the template itself?
The text was updated successfully, but these errors were encountered: