Instructions to use Boojum/g4c-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Boojum/g4c-4bit with Transformers:

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

pipe = pipeline("text-generation", model="Boojum/g4c-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Boojum/g4c-4bit")
model = AutoModelForCausalLM.from_pretrained("Boojum/g4c-4bit")
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 Boojum/g4c-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Boojum/g4c-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Boojum/g4c-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Boojum/g4c-4bit

SGLang

How to use Boojum/g4c-4bit 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 "Boojum/g4c-4bit" \
    --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": "Boojum/g4c-4bit",
		"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 "Boojum/g4c-4bit" \
        --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": "Boojum/g4c-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Boojum/g4c-4bit with Docker Model Runner:
```
docker model run hf.co/Boojum/g4c-4bit
```

Boojum commited on Nov 6, 2025

Commit

4bb0b1b

verified ·

1 Parent(s): 8fe7a71

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

chat_template.jinja +2 -3

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,3 @@
-{# Chat template fixes by Unsloth #}
 {#-
   In addition to the normal inputs of `messages` and `tools`, this template also accepts the
   following kwargs:
@@ -192,6 +191,7 @@
         {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
     {%- endif -%}
 {%- endmacro -%}
 {#- System Message Construction ============================================ #}
 {%- macro build_system_message() -%}
@@ -341,5 +341,4 @@
 {#- Generation prompt #}
 {%- if add_generation_prompt -%}
 <|start|>assistant
-{%- endif -%}
-{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}

 {#-
   In addition to the normal inputs of `messages` and `tools`, this template also accepts the
   following kwargs:
         {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
     {%- endif -%}
 {%- endmacro -%}
+{#- [|}oojum #}
 {#- System Message Construction ============================================ #}
 {%- macro build_system_message() -%}
 {#- Generation prompt #}
 {%- if add_generation_prompt -%}
 <|start|>assistant
+{%- endif -%}