Instructions to use alpindale/miquella-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alpindale/miquella-120b with Transformers:

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

pipe = pipeline("text-generation", model="alpindale/miquella-120b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alpindale/miquella-120b")
model = AutoModelForCausalLM.from_pretrained("alpindale/miquella-120b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alpindale/miquella-120b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alpindale/miquella-120b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alpindale/miquella-120b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alpindale/miquella-120b

SGLang

How to use alpindale/miquella-120b 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 "alpindale/miquella-120b" \
    --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": "alpindale/miquella-120b",
		"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 "alpindale/miquella-120b" \
        --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": "alpindale/miquella-120b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alpindale/miquella-120b with Docker Model Runner:
```
docker model run hf.co/alpindale/miquella-120b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Miquella 120B

Model has been remade with the fixed dequantization of miqu.

This is a merge of pre-trained language models created using mergekit. An attempt at re-creating goliath-120b using the new miqu-1-70b model instead of Xwin.

The merge ratios are the same as goliath, only that Xwin is swapped with miqu.

Models Merged

The following models were included in the merge:

Miquella the Unalloyed, by @eldrtchmoon

Downloads last month: 38

Safetensors

Model size

118B params

Tensor type

F16

Model tree for alpindale/miquella-120b

Quantizations

2 models