Instructions to use QuixiAI/samantha-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuixiAI/samantha-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuixiAI/samantha-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("QuixiAI/samantha-7b") model = AutoModelForCausalLM.from_pretrained("QuixiAI/samantha-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use QuixiAI/samantha-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuixiAI/samantha-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuixiAI/samantha-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/QuixiAI/samantha-7b
- SGLang
How to use QuixiAI/samantha-7b 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 "QuixiAI/samantha-7b" \ --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": "QuixiAI/samantha-7b", "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 "QuixiAI/samantha-7b" \ --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": "QuixiAI/samantha-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use QuixiAI/samantha-7b with Docker Model Runner:
docker model run hf.co/QuixiAI/samantha-7b
I do not understand if this is a serious training, with sufficient data
#1
by DaDavinci - opened
"She will not engage in roleplay, romance, or sexual activity."
Now what would be a application for such an assistant? opening doors for clients?
Might be useful (or game changer) in some genre of video games/virtual experiences
She will not engage in roleplay, romance, or sexual activity.
But those are the only applications I care about smh.
I built Samantha not for a commercial purpose. She's an experiment in social artificial intelligence. I want to see what happens. Especially as she gets smarter.