Downloads · 30 days
9
21% of all-time downloads
broken-model-chat-template-fix
SriM/broken-model-chat-template-fix
broken-model-chat-template-fix is a text generation model from SriM. Use it when you need the model to write or continue text. It is set up for transformers.
Some /chat/completions servers render messages into a prompt using tokenizer.applychattemplate().
All-time downloads
43
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- Jan 9, 2026
- Updated
- Jan 9, 2026
- SHA
- cdc428a4
Try a prompt
Base models
Model card
From the Hugging Face model README
Summary of the issue
Some /chat/completions servers render messages into a prompt using tokenizer.apply_chat_template().
Root cause
tokenizer_config.json was missing chat_template.
Without this chat-based inference servers cannot format prompts correctly.
Minimal fix
Added one key to tokenizer_config.json:
chat_template
No weight files or other configs were modified.
Why these changes were necessary
A chat template is the bridge between the structured messages such as system, user, assistant and a single serialized prompt string or tokens that matches training conventions
When the template is missing, transformers cannot reliably:
-
render conversation history,
-
Insert the assistant generation boundary correctly, and
-
ensure consistent behavior across pipelines (pipeline("text-generation"), chat wrappers, etc.).
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Created
- Jan 9, 2026
- Updated
- Jan 9, 2026