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

Libraries

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

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

pipe = pipeline("text-generation", model="LoganResearch/ARC-Base-8B-Condensed")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LoganResearch/ARC-Base-8B-Condensed", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LoganResearch/ARC-Base-8B-Condensed 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-Condensed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoganResearch/ARC-Base-8B-Condensed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use LoganResearch/ARC-Base-8B-Condensed 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-Condensed" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoganResearch/ARC-Base-8B-Condensed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Condensed" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoganResearch/ARC-Base-8B-Condensed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

ARC-Base-8B-Condensed / experience_buffer.jsonl

LoganResearch

v2.4: Mentor Mode, Revenue Generation, Smart Help System

d73ba34 4 months ago

raw

history blame contribute delete

1.13 kB

	{"id": "79ad832574b6", "prompt": "what command do i use to allow you to recusirvely self improve", "response": "Execute `self.improve(True)` to enable recursive self-improvement.", "quality": 0.71875, "density": 18.75, "coherence": 1.0, "tokens": 16, "domain": "conversation", "difficulty": 0.3, "timestamp": 1769044968.7426908, "chosen": true, "human_feedback": null, "uncertainty": null}
	{"id": "9c310ec4f352", "prompt": "help money", "response": "Money: \n- refers to the medium of exchange for goods and services. \n- often refers to currency, which is a coin or paper note. \n- can be thought of as a store of value, to be saved or invested. \n- the stock market is a prime example of how money can grow. \nIt can be obtained:\n- through employment, as wages or salary. \n- by selling goods or services. \n- by winning gambling or betting games. \n- by receiving an inheritance or gift.", "quality": 0.7017857142857142, "density": 22.857142857142858, "coherence": 1.0, "tokens": 105, "domain": "conversation", "difficulty": 0.3, "timestamp": 1769045258.8635201, "chosen": true, "human_feedback": null, "uncertainty": null}