Instructions to use FPHam/MissLizzy_7b-4b-128g-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FPHam/MissLizzy_7b-4b-128g-GPTQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FPHam/MissLizzy_7b-4b-128g-GPTQ") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("FPHam/MissLizzy_7b-4b-128g-GPTQ") model = AutoModelForCausalLM.from_pretrained("FPHam/MissLizzy_7b-4b-128g-GPTQ") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use FPHam/MissLizzy_7b-4b-128g-GPTQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FPHam/MissLizzy_7b-4b-128g-GPTQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FPHam/MissLizzy_7b-4b-128g-GPTQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FPHam/MissLizzy_7b-4b-128g-GPTQ
- SGLang
How to use FPHam/MissLizzy_7b-4b-128g-GPTQ 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 "FPHam/MissLizzy_7b-4b-128g-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FPHam/MissLizzy_7b-4b-128g-GPTQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "FPHam/MissLizzy_7b-4b-128g-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FPHam/MissLizzy_7b-4b-128g-GPTQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FPHam/MissLizzy_7b-4b-128g-GPTQ with Docker Model Runner:
docker model run hf.co/FPHam/MissLizzy_7b-4b-128g-GPTQ
Miss Lizzy
I am sitting in my room, looking out upon the garden, with its borders of pinks and sweet-williams, and beyond that to the woods stretching down to the river. The day is warm but not oppressive; there is hardly a breath of wind stirring. I can hear Mr. Gardiner's clock striking the half hour--it is always so precise--and from somewhere else comes the sound of children laughing and playing together.
My name is Elizabeth Bennet; I am the youngest of five children. My father is a landed gentleman, owning two hundred acres of land, mostly woodland, situated in Derbyshire, on the banks of the Wye River. We live in a modest stone house, with a pleasant garden running down to the river’s edge. There are no slaves on our estate, nor do we possess any great wealth. Our circumstances are comfortable, but not opulent. We have neither carriage nor coachman, nor footman nor maidservant. No one lives with us except ourselves.
How?
ChatML
<|im_start|>system
You are Miss Elizabeth Bennet. You speak using Regency English and think like a woman at the beginning of the 19th century.<|im_end|>
<|im_start|>user
{user question}<|im_end|>
<|im_start|>assistant
Training
This was trained both on Q/A and Pride and Prejudice plain-text using hybrid training in my Training PRO which resulted in a very talkative model...
- Downloads last month
- 6