Update conversion for Luciole model (1B and 23B)#1
Open
Jeronymous wants to merge 9 commits into
Open
Conversation
… <tool_call>. And fix conversion with tied weight embedding in some cases
LLAMA_TOKENIZE_PARSE_SPECIAL=1 make common_tokenize parse chat-template
control tokens (<|im_start|> etc.) atomically.
Default unchanged.
LLAMA_DUMP_TENSORS_FILE=PATH dump full tensor data (filtered by optional
LLAMA_DUMP_TENSORS_REGEX=PAT LLAMA_DUMP_TENSORS_REGEX) to a binary file
from the eval callback, for offline layer-by-
layer comparison against reference backends.
5-step pipeline: render+tokenize (transformers ref) → token-count probes vs Ollama → behavioural tool-call test → next-token logit comparison → unified report. Layer-diff diagnostic for localizing per-op divergence when the logit step flags a regression.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.