Instructions to use ATL-Machine/affine-0KB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ATL-Machine/affine-0KB with Transformers:

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

pipe = pipeline("text-generation", model="ATL-Machine/affine-0KB")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ATL-Machine/affine-0KB")
model = AutoModelForCausalLM.from_pretrained("ATL-Machine/affine-0KB")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ATL-Machine/affine-0KB with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ATL-Machine/affine-0KB"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ATL-Machine/affine-0KB",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ATL-Machine/affine-0KB

SGLang

How to use ATL-Machine/affine-0KB 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 "ATL-Machine/affine-0KB" \
    --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": "ATL-Machine/affine-0KB",
		"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 "ATL-Machine/affine-0KB" \
        --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": "ATL-Machine/affine-0KB",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ATL-Machine/affine-0KB with Docker Model Runner:
```
docker model run hf.co/ATL-Machine/affine-0KB
```

affine-0KB

Commit History

doc: update doc

6c9a3f7

wilfrid51 commited on Dec 18, 2025

README

76de2c9

wilfrid51 commited on Dec 18, 2025

Track tokenizer.json with LFS

6643fd3

wilfrid51 commited on Dec 17, 2025

init

5a7855d

wilfrid51 commited on Dec 17, 2025

Initial upload

6be5d63

wilfrid51 commited on Dec 17, 2025

initial commit

f992bb3
verified

ATL-Machine commited on Dec 17, 2025

Commit History

doc: update doc 6c9a3f7

README 76de2c9

Track tokenizer.json with LFS 6643fd3

init 5a7855d

Initial upload 6be5d63

initial commit f992bb3 verified

doc: update doc

6c9a3f7

README

76de2c9

Track tokenizer.json with LFS

6643fd3

init

5a7855d

Initial upload

6be5d63

initial commit

f992bb3
verified