Instructions to use matt0xdev/Affine-dark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use matt0xdev/Affine-dark with Transformers:

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

pipe = pipeline("text-generation", model="matt0xdev/Affine-dark")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matt0xdev/Affine-dark")
model = AutoModelForCausalLM.from_pretrained("matt0xdev/Affine-dark", 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 matt0xdev/Affine-dark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "matt0xdev/Affine-dark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "matt0xdev/Affine-dark",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/matt0xdev/Affine-dark

SGLang

How to use matt0xdev/Affine-dark 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 "matt0xdev/Affine-dark" \
    --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": "matt0xdev/Affine-dark",
		"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 "matt0xdev/Affine-dark" \
        --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": "matt0xdev/Affine-dark",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use matt0xdev/Affine-dark with Docker Model Runner:
```
docker model run hf.co/matt0xdev/Affine-dark
```

Affine-dark / tmp_chute.py

matt0xdev

Upload folder using huggingface_hub

51da8e9 verified 11 months ago

Raw

History Blame Contribute Delete

885 Bytes


	import os
	from chutes.chute import NodeSelector
	from chutes.chute.template.sglang import build_sglang_chute
	os.environ["NO_PROXY"] = "localhost,127.0.0.1"

	chute = build_sglang_chute(
	username="ryan888",
	readme="matt0xdev/affine-5CY88hoZChb9NGTvss5LDHddPrmZ4LJb4q2cSESAVoAt1qcX",
	model_name="matt0xdev/affine-5CY88hoZChb9NGTvss5LDHddPrmZ4LJb4q2cSESAVoAt1qcX",
	image="chutes/sglang:nightly-2025091100",
	concurrency=24,
	revision="8a9ca7839281a9b859a04a4c7c2350718fe89975",
	node_selector=NodeSelector(
	gpu_count=8,
	include=["h100_nvl", "pro_6000", "l40", "a40", "a100", "a100_sxm", "h800", "h100", "a6000_ada", "h20", "l40s", "h200"],
	),
	engine_args=(
	"--context-length 262144 "
	"--tool-call-parser qwen25 "
	"--attention-backend fa3 "
	"--cuda-graph-max-bs 24 "
	),
	shutdown_after_seconds=1600,
	)