run : fix BOS being added to each message #11302
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Porting the fix from simple-chat. Signed-off-by: Eric Curtin <ecurtin@redhat.com>
ggerganov
approved these changes
Jan 20, 2025
Comment on lines
+736
to
+737
| if (llama_tokenize(vocab, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), | ||
| llama_get_kv_cache_used_cells(llama_data.context.get()) == 0, true) < 0) { |
There was a problem hiding this comment.
Suggested change
| if (llama_tokenize(vocab, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), | |
| llama_get_kv_cache_used_cells(llama_data.context.get()) == 0, true) < 0) { | |
| if (llama_tokenize(vocab, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), | |
| is_first, true) < 0) { |
There was a problem hiding this comment.
Following the simple-chat example, the first call to llama_tokenize uses this parameter:
is_first
and the second uses:
llama_get_kv_cache_used_cells(llama_data.context.get()) == 0
There was a problem hiding this comment.
Ah, I didn't even notice. Maybe this way it is better than introducing the is_first parameter.
There was a problem hiding this comment.
Not pretending I know the details and just copying simple-chat :)
There was a problem hiding this comment.
I pushed this variant to both simple-chat and run - seems much simpler than the is_first solution: #11311
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Porting the fix from simple-chat.