Instructions to use therealcyberlord/MindGem-9b-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use therealcyberlord/MindGem-9b-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="therealcyberlord/MindGem-9b-bnb-4bit")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("therealcyberlord/MindGem-9b-bnb-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use therealcyberlord/MindGem-9b-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "therealcyberlord/MindGem-9b-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "therealcyberlord/MindGem-9b-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/therealcyberlord/MindGem-9b-bnb-4bit

SGLang

How to use therealcyberlord/MindGem-9b-bnb-4bit 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 "therealcyberlord/MindGem-9b-bnb-4bit" \
    --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": "therealcyberlord/MindGem-9b-bnb-4bit",
		"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 "therealcyberlord/MindGem-9b-bnb-4bit" \
        --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": "therealcyberlord/MindGem-9b-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use therealcyberlord/MindGem-9b-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/therealcyberlord/MindGem-9b-bnb-4bit
```

Model Description:

MindGem is a specialized model for mental health therapy, trained on over 8,000 therapy interactions. Designed to guide users through challenging situations, it can be run locally to ensure complete privacy in conversations.

Training details

Fine-tuned for one epoch on the training set, you can find more details here: https://tinyurl.com/mr3ehnuz

Uploaded model

Developed by: Xingyu
License: apache-2.0
Finetuned from model : unsloth/gemma-2-9b-bnb-4bit

This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for therealcyberlord/MindGem-9b-bnb-4bit

Base model

google/gemma-2-9b

Quantized

unsloth/gemma-2-9b-bnb-4bit

Finetuned

(480)

this model

therealcyberlord
/

MindGem-9b-bnb-4bit

Model Description:

Training details

Uploaded model

Model tree for therealcyberlord/MindGem-9b-bnb-4bit

Dataset used to train therealcyberlord/MindGem-9b-bnb-4bit