Instructions to use Hypersniper/The_OverThinker_Phi_1_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hypersniper/The_OverThinker_Phi_1_5 with Transformers:

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

pipe = pipeline("text-generation", model="Hypersniper/The_OverThinker_Phi_1_5", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Hypersniper/The_OverThinker_Phi_1_5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Hypersniper/The_OverThinker_Phi_1_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hypersniper/The_OverThinker_Phi_1_5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hypersniper/The_OverThinker_Phi_1_5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hypersniper/The_OverThinker_Phi_1_5

SGLang

How to use Hypersniper/The_OverThinker_Phi_1_5 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 "Hypersniper/The_OverThinker_Phi_1_5" \
    --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": "Hypersniper/The_OverThinker_Phi_1_5",
		"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 "Hypersniper/The_OverThinker_Phi_1_5" \
        --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": "Hypersniper/The_OverThinker_Phi_1_5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hypersniper/The_OverThinker_Phi_1_5 with Docker Model Runner:
```
docker model run hf.co/Hypersniper/The_OverThinker_Phi_1_5
```

Welcome to The OverThinker's Repository!

The OverThinker working late at night trying to find that answer for you.

Buy me Ko-fi

Meet The OverThinker! While some might argue he digs way too deep, many regard him as a genius. This repository is where his complex thoughts and innovative solutions come to life.

Model Phi 1.5

The OverThinker operates on the small Model Phi 1.5, uniquely tailored to offer intriguing perspectives:

Specialized in Riddles: Overfitted, by design, on a comprehensive Riddles database. Mr OverThinker is not just another bot – he's an enigma wrapped in a mystery.
Built on the Alpaca Template

template = ("Below is an instruction that describes a task, paired with an input "
            "that provides further context. Write a response that appropriately "
            "completes the request.\n\n### Instruction:\n{query}\n\n### Response:\n")

# Example of using the template with a query
query = "What gets wetter as it dries?"
formatted_string = template.format(query=query)

How to Interact with Mr OverThinker

Here is how you can get started:

How to Interact with OverThinker using Web Generation WebUI (click to expand)

Install text generation webui Text Generation WebUI.
On the 'Model' tab enter this URL Hypersniper/The_OverThinker_Phi_1_5 to automatically download the model.
On the same tab, select the model, make sure trust-remote-code is checked, then Load the model.
Next, on the Parameters table, select Instruction Template and make sure the Alpaca template is selected.
Lastly, under Mode, select Chat and then Instruct. Now you are ready to chat with The OverThinker. Enjoy!

The OverThinker awaits your challenging riddles and is ready to provide you with wild answers. Let the journey begin!

Conversation Examples

Downloads last month: 15

Hypersniper
/

The_OverThinker_Phi_1_5

Welcome to The OverThinker's Repository!

Model Phi 1.5

How to Interact with Mr OverThinker

Conversation Examples

Dataset used to train Hypersniper/The_OverThinker_Phi_1_5