Instructions to use testmoto/gemma-2-9b-mix_coding_magpie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use testmoto/gemma-2-9b-mix_coding_magpie with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="testmoto/gemma-2-9b-mix_coding_magpie")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("testmoto/gemma-2-9b-mix_coding_magpie") model = AutoModelForCausalLM.from_pretrained("testmoto/gemma-2-9b-mix_coding_magpie") - MLX
How to use testmoto/gemma-2-9b-mix_coding_magpie with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("testmoto/gemma-2-9b-mix_coding_magpie") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- vLLM
How to use testmoto/gemma-2-9b-mix_coding_magpie with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "testmoto/gemma-2-9b-mix_coding_magpie" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "testmoto/gemma-2-9b-mix_coding_magpie", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/testmoto/gemma-2-9b-mix_coding_magpie
- SGLang
How to use testmoto/gemma-2-9b-mix_coding_magpie 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 "testmoto/gemma-2-9b-mix_coding_magpie" \ --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": "testmoto/gemma-2-9b-mix_coding_magpie", "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 "testmoto/gemma-2-9b-mix_coding_magpie" \ --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": "testmoto/gemma-2-9b-mix_coding_magpie", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - MLX LM
How to use testmoto/gemma-2-9b-mix_coding_magpie with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "testmoto/gemma-2-9b-mix_coding_magpie" --prompt "Once upon a time"
- Docker Model Runner
How to use testmoto/gemma-2-9b-mix_coding_magpie with Docker Model Runner:
docker model run hf.co/testmoto/gemma-2-9b-mix_coding_magpie
testmoto/gemma-2-9b-mix_coding_magpie
The Model testmoto/gemma-2-9b-mix_coding_magpie was converted to MLX format from testmoto/gemma-2-llm2024-dpo-02 using mlx-lm version 0.20.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("testmoto/gemma-2-9b-mix_coding_magpie")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 79
Model size
9B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for testmoto/gemma-2-9b-mix_coding_magpie
Base model
testmoto/gemma-2-llm2024-01 Finetuned
testmoto/gemma-2-llm2024-dpo-02