Instructions to use grimpep/Huginnstruct-22B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimpep/Huginnstruct-22B with Transformers:

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

pipe = pipeline("text-generation", model="grimpep/Huginnstruct-22B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimpep/Huginnstruct-22B")
model = AutoModelForCausalLM.from_pretrained("grimpep/Huginnstruct-22B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimpep/Huginnstruct-22B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimpep/Huginnstruct-22B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimpep/Huginnstruct-22B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimpep/Huginnstruct-22B

SGLang

How to use grimpep/Huginnstruct-22B 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 "grimpep/Huginnstruct-22B" \
    --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": "grimpep/Huginnstruct-22B",
		"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 "grimpep/Huginnstruct-22B" \
        --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": "grimpep/Huginnstruct-22B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimpep/Huginnstruct-22B with Docker Model Runner:
```
docker model run hf.co/grimpep/Huginnstruct-22B
```

           [Experimental model]

This model is an experiment using the frankenstein script from https://huggingface.co/chargoddard/llama2-22b BLOCK_DIAGONAL = False

Using: https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16 + Then used https://huggingface.co/upstage/llama-30b-instruct-2048 as donor model.

It used 160GB of system ram to merge these models, they merge fast without swap.

For prompt template and model information see huginnV1.

Downloads last month: 5