Instructions to use LoganResearch/ARC-Base-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoganResearch/ARC-Base-8B with Transformers:

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

pipe = pipeline("text-generation", model="LoganResearch/ARC-Base-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoganResearch/ARC-Base-8B")
model = AutoModelForCausalLM.from_pretrained("LoganResearch/ARC-Base-8B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

HERMES

How to use LoganResearch/ARC-Base-8B with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LoganResearch/ARC-Base-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoganResearch/ARC-Base-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoganResearch/ARC-Base-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LoganResearch/ARC-Base-8B

SGLang

How to use LoganResearch/ARC-Base-8B 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 "LoganResearch/ARC-Base-8B" \
    --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": "LoganResearch/ARC-Base-8B",
		"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 "LoganResearch/ARC-Base-8B" \
        --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": "LoganResearch/ARC-Base-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LoganResearch/ARC-Base-8B with Docker Model Runner:
```
docker model run hf.co/LoganResearch/ARC-Base-8B
```

ARC-Base-8B

Commit History

Jan 19

20:00
Add demo video

LoganResearch

Verified signature
371236c
19:00
Fix device mismatch and tensor.item() bugs

LoganResearch

Verified signature
749c71a
18:15
Fix model card image (was empty)

LoganResearch

Verified signature
9728955
18:14
Fix image URL to full path

LoganResearch

Verified signature
5166bad
18:11
Add model card image to README

LoganResearch

Verified signature
e624897
18:09
Add model card image

LoganResearch

Verified signature
1f1e15f
18:08
Scientific model card v2 - Logan Matthew Napolitano

LoganResearch

Verified signature
b7c1661
18:03
Comprehensive scientific model card - Logan Matthew Napolitano

LoganResearch

Verified signature
858276a
17:54
Scientific model card - Logan Matthew Napolitano

LoganResearch

Verified signature
719d0c4
17:53
Scientific model card - Logan Matthew Napolitano

LoganResearch

Verified signature
15bc491
17:52
Delete README.md

LoganResearch

Verified signature
3bdb9c3
17:46
Upload README.md with huggingface_hub

LoganResearch

Verified signature
7813639
17:46
Upload inference.py with huggingface_hub

LoganResearch

Verified signature
1f68519
17:41
Upload sycophancy_head.pt with huggingface_hub

LoganResearch

Verified signature
a5f7b81
17:41
Upload verbosity_head.pt with huggingface_hub

LoganResearch

Verified signature
55c6a88
17:41
Upload hedging_head.pt with huggingface_hub

LoganResearch

Verified signature
1c3352c
17:41
Upload risk_predictor.pt with huggingface_hub

LoganResearch

Verified signature
e68ffdc
17:41
Upload adapter_config.json with huggingface_hub

LoganResearch

Verified signature
74db39f
17:41
Upload adapter_model.safetensors with huggingface_hub

LoganResearch

Verified signature
df25240
16:19
Rename ubermenschetien_cfhot900loc_clone.py to Ubermenschetien.py

LoganResearch

Verified signature
334051a
16:18
Upload ubermenschetien_cfhot900loc_clone.py⁠

LoganResearch

Verified signature
2f108d7

Jan 18

01:29
Create Alignment.py

LoganResearch

Verified signature
bc32f38

Jan 17

22:03
Update README.md

LoganResearch

Verified signature
36c2f7a
22:02
Create README.md

LoganResearch

Verified signature
9927b2c
21:50
Upload Übermenschetien-8B base model

LoganResearch

Verified signature
c1edb01
21:49
initial commit

LoganResearch

Verified signature
f1407b1

Commit History

Jan 19

Add demo video

Fix device mismatch and tensor.item() bugs

Fix model card image (was empty)

Fix image URL to full path

Add model card image to README

Add model card image

Scientific model card v2 - Logan Matthew Napolitano

Comprehensive scientific model card - Logan Matthew Napolitano

Scientific model card - Logan Matthew Napolitano

Scientific model card - Logan Matthew Napolitano

Delete README.md

Upload README.md with huggingface_hub

Upload inference.py with huggingface_hub

Upload sycophancy_head.pt with huggingface_hub

Upload verbosity_head.pt with huggingface_hub

Upload hedging_head.pt with huggingface_hub

Upload risk_predictor.pt with huggingface_hub

Upload adapter_config.json with huggingface_hub

Upload adapter_model.safetensors with huggingface_hub

Rename ubermenschetien_cfhot900loc_clone.py to Ubermenschetien.py

Upload ubermenschetien_cfhot900loc_clone.py⁠

Jan 18

Create Alignment.py

Jan 17

Update README.md

Create README.md

Upload Übermenschetien-8B base model

initial commit