Instructions to use theNovaAI/Hypernova-experimental-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theNovaAI/Hypernova-experimental-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="theNovaAI/Hypernova-experimental-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("theNovaAI/Hypernova-experimental-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("theNovaAI/Hypernova-experimental-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use theNovaAI/Hypernova-experimental-GPTQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/theNovaAI/Hypernova-experimental-GPTQ

SGLang

How to use theNovaAI/Hypernova-experimental-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 "theNovaAI/Hypernova-experimental-GPTQ" \
    --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": "theNovaAI/Hypernova-experimental-GPTQ",
		"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 "theNovaAI/Hypernova-experimental-GPTQ" \
        --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": "theNovaAI/Hypernova-experimental-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use theNovaAI/Hypernova-experimental-GPTQ with Docker Model Runner:
```
docker model run hf.co/theNovaAI/Hypernova-experimental-GPTQ
```

Hypernova-experimental

Quantized to 4bit 128g using AutoGPTQ and 🤗 Optimum

Tried some new stuff this time around. Very different outcome than I expected. This is an experimental model that was created for the development of NovaAI.

Good at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.

Prompt Template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:

Models Merged

The following models were included in the merge:

Some finetuning done as well

Downloads last month: 2

Model tree for theNovaAI/Hypernova-experimental-GPTQ

Base model

Gryphe/MythoMax-L2-13b

Quantized

(16)

this model

Collection including theNovaAI/Hypernova-experimental-GPTQ

Hypernova

Collection

Experimental series of models, largely untested • 5 items • Updated Feb 3, 2025