Instructions to use appvoid/arco-2-reasoning-20k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use appvoid/arco-2-reasoning-20k with Transformers:

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

pipe = pipeline("text-generation", model="appvoid/arco-2-reasoning-20k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("appvoid/arco-2-reasoning-20k")
model = AutoModelForCausalLM.from_pretrained("appvoid/arco-2-reasoning-20k")
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

vLLM

How to use appvoid/arco-2-reasoning-20k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/arco-2-reasoning-20k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/arco-2-reasoning-20k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/appvoid/arco-2-reasoning-20k

SGLang

How to use appvoid/arco-2-reasoning-20k 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 "appvoid/arco-2-reasoning-20k" \
    --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": "appvoid/arco-2-reasoning-20k",
		"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 "appvoid/arco-2-reasoning-20k" \
        --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": "appvoid/arco-2-reasoning-20k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use appvoid/arco-2-reasoning-20k with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for appvoid/arco-2-reasoning-20k to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for appvoid/arco-2-reasoning-20k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for appvoid/arco-2-reasoning-20k to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="appvoid/arco-2-reasoning-20k",
    max_seq_length=2048,
)

Docker Model Runner
How to use appvoid/arco-2-reasoning-20k with Docker Model Runner:
```
docker model run hf.co/appvoid/arco-2-reasoning-20k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

Developed by: appvoid
License: apache-2.0
Finetuned from model : appvoid/arco-2

fine-tuned on 20k samples from KingNish reasoning dataset

format is like the template in the dataset:

<|im_start|>user
What is javascript?
<|im_end|>
<|im_start|>reasoning
I can answer directly to this question.
<|im_end|>
<|im_start|>assistant
That's a great question! JavaScript is a programming language that is commonly used to create interactive web pages and applications. It's known for its ability to create dynamic, interactive content and it's used by many web developers to create web pages, mobile applications, and more.

Downloads last month: 1

Model tree for appvoid/arco-2-reasoning-20k

Base model

appvoid/arco-2

Finetuned

(11)

this model

Merges

21 models

Quantizations

3 models