Instructions to use andrewbrown/gpt2-mi-reflector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andrewbrown/gpt2-mi-reflector with Transformers:

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

pipe = pipeline("text-generation", model="andrewbrown/gpt2-mi-reflector")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andrewbrown/gpt2-mi-reflector")
model = AutoModelForCausalLM.from_pretrained("andrewbrown/gpt2-mi-reflector")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use andrewbrown/gpt2-mi-reflector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andrewbrown/gpt2-mi-reflector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andrewbrown/gpt2-mi-reflector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/andrewbrown/gpt2-mi-reflector

SGLang

How to use andrewbrown/gpt2-mi-reflector 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 "andrewbrown/gpt2-mi-reflector" \
    --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": "andrewbrown/gpt2-mi-reflector",
		"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 "andrewbrown/gpt2-mi-reflector" \
        --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": "andrewbrown/gpt2-mi-reflector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use andrewbrown/gpt2-mi-reflector with Docker Model Runner:
```
docker model run hf.co/andrewbrown/gpt2-mi-reflector
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GPT2-MI-Reflector

A gpt2 based motivational interviewing reflector

Given a prompt and a response, this GPT2 based transformer will generate a reflection. It was fine-tuned on prompt/response/reflection triplets so it should also be inferenced with the same input style. Examples are shown below.

The triplets this reflector was fine-tuned on focus on smoking-cessation. Given this, its best performance is when inferencing about smoking.

To properly inference model (as it was fine-tuned), use the following format:

Prompt: ...Question from bot...

Response: ...Response from user...

Example Prompt: paste two lines below and generate a reflection

Prompt: What do you want to change in your smoking?

Response: I want to smoke less often in my life, its become quite stressful for me.

Model should generate a motivational interviewing adherent statement

Downloads last month: 6

Model tree for andrewbrown/gpt2-mi-reflector

Quantizations

1 model