Instructions to use freecs/ArtificialThinker-Phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use freecs/ArtificialThinker-Phi2 with Transformers:

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

pipe = pipeline("text-generation", model="freecs/ArtificialThinker-Phi2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("freecs/ArtificialThinker-Phi2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use freecs/ArtificialThinker-Phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "freecs/ArtificialThinker-Phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "freecs/ArtificialThinker-Phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/freecs/ArtificialThinker-Phi2

SGLang

How to use freecs/ArtificialThinker-Phi2 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 "freecs/ArtificialThinker-Phi2" \
    --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": "freecs/ArtificialThinker-Phi2",
		"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 "freecs/ArtificialThinker-Phi2" \
        --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": "freecs/ArtificialThinker-Phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use freecs/ArtificialThinker-Phi2 with Docker Model Runner:
```
docker model run hf.co/freecs/ArtificialThinker-Phi2
```

The First Open-Source Reasoning LLM

December 28, 2023 - This model was created 11 months before OpenAI's o1 release.

Historical Context

In late 2023, I was experimenting with fine-tuning open-source models. Working with limited computational resources (primarily free Colab notebooks with T4 GPUs), I focused on developing novel approaches and new paradigms to significantly enhance LLM capabilities without simply scaling the number of parameters, since that would have required substantial computational resources.

Proof of timeline: Check the initial commit - December 28, 2023.

Technical Approach

The model uses a custom chat template that includes a "reasoning" step before providing the output to the user:

<|system|>sys_message
<|prompt|>prompt
<|reasoning|>reasoning
<|response|>response<|endoftext|>

To test this approach, I created the ArtificialThinkerSet dataset to fine-tune Phi-2.

I also wrote "Reasoning Is All You Need" - a blog post explaining this approach.

You can find me at gr.bio.

Downloads last month: 31

Safetensors

Model size

3B params

Tensor type

F16

Model tree for freecs/ArtificialThinker-Phi2

Base model

microsoft/phi-2

Finetuned

(410)

this model

Merges

1 model

freecs
/

ArtificialThinker-Phi2

The First Open-Source Reasoning LLM

Historical Context

Technical Approach

Model tree for freecs/ArtificialThinker-Phi2

Dataset used to train freecs/ArtificialThinker-Phi2