Hugging Face's logo

google
/
functiongemma-270m-it

Text Generation
Transformers
Safetensors
gemma3_text
gemma3
gemma
google
functiongemma
conversational
text-generation-inference
Model card Files
xet
Community
11

Fixing MLX stop tokens

#3
by prince-canuma - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+4
-2
initial commit5e35b798
agentgemma init9b70ba3c
update chat template to better match function calling format expectations5bec583d
 Updated chat template233260dc
 Remove autoescape from chat templated4191262
add support for objects and arrays in call/responses4adfa3ff
 Fix newlines (#1)b976196d
Fix tool response handling in chat template7ac5cbba
Add support for enums and developer role.587aa0a8
Removing whitespace and fixing boolean argument encoding.3957bbea
Ensure newline after `<start_of_turn>model`168b32c7
Use explicit newline chars0b1a618f
Handle empty params and properties in chat templatea5c6f81e
Support multiple FCs and FRs.99db3a11
Updates to formatting42845279
Handle union input types more appropriately.fefd1b60
Remove unneeded sort that causes crashesf0b063a8
Add <start_function_response> token if last message is a tool_call.c108878e
Better support union list types and single value list types.c352f5a0
push 2025-12-09 checkpointdad1c0c0
Support parallel tool responese in template86a84391
Handle cases when tools is not supplied and when arguments is notb3b8228c
Update chat_template.jinjaa3760e22
Rebase on stable v4.57.3.b7994ded
 Update README.mdf0d450bf
 Update README.md9d53b902
 Update README.md98537068
 Update README.mdf7bd1395
 Upload tiny_garden.litertlm8b4fdc78
 Update README.md23f397c9
prince-canuma
No description provided.
Fixing MLX stop tokens01e6ec68
canyon289

We need to change the stop token to be 1 and 50 (not 49)
canyon289

Made stop token edit here https://huggingface.co/google/functiongemma-270m-it/discussions/4

Cannot merge
This branch has merge conflicts in the following files:
  • README.md
  • config.json

Sign up or log in to comment