Instructions to use SriM/broken-model-chat-template-fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SriM/broken-model-chat-template-fix with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SriM/broken-model-chat-template-fix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SriM/broken-model-chat-template-fix")
model = AutoModelForCausalLM.from_pretrained("SriM/broken-model-chat-template-fix", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SriM/broken-model-chat-template-fix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SriM/broken-model-chat-template-fix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SriM/broken-model-chat-template-fix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SriM/broken-model-chat-template-fix

SGLang

How to use SriM/broken-model-chat-template-fix with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SriM/broken-model-chat-template-fix" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SriM/broken-model-chat-template-fix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SriM/broken-model-chat-template-fix" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SriM/broken-model-chat-template-fix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SriM/broken-model-chat-template-fix with Docker Model Runner:
```
docker model run hf.co/SriM/broken-model-chat-template-fix
```

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.).

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for SriM/broken-model-chat-template-fix

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1498)

this model