Instructions to use KoboldAI/OPT-6.7B-Nerybus-Mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/OPT-6.7B-Nerybus-Mix with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/OPT-6.7B-Nerybus-Mix")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/OPT-6.7B-Nerybus-Mix")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/OPT-6.7B-Nerybus-Mix")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KoboldAI/OPT-6.7B-Nerybus-Mix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/OPT-6.7B-Nerybus-Mix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/OPT-6.7B-Nerybus-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/OPT-6.7B-Nerybus-Mix

SGLang

How to use KoboldAI/OPT-6.7B-Nerybus-Mix 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 "KoboldAI/OPT-6.7B-Nerybus-Mix" \
    --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": "KoboldAI/OPT-6.7B-Nerybus-Mix",
		"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 "KoboldAI/OPT-6.7B-Nerybus-Mix" \
        --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": "KoboldAI/OPT-6.7B-Nerybus-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/OPT-6.7B-Nerybus-Mix with Docker Model Runner:
```
docker model run hf.co/KoboldAI/OPT-6.7B-Nerybus-Mix
```

OPT-6.7B-Nerybus-Mix

This is an experimental model containing a parameter-wise 50/50 blend (weighted average) of the weights of NerysV2-6.7B and ErebusV1-6.7B Preliminary testing produces pretty coherent outputs, however, it seems less impressive than the 2.7B variant of Nerybus, as both 6.7B source models appear more similar than their 2.7B counterparts.

License

The two models used for this blend, NerysV2-6.7B and ErebusV1-6.7B are made by Mr. Seeker.

https://huggingface.co/KoboldAI/OPT-6.7B-Erebus

Evaluation Results

No formal evaluation is available for this model at this time. This blend was created in FP16, due to available memory constraints.

It is recommend to use this model with the KoboldAI software. All feedback and comments can be directed to Concedo on the KoboldAI discord.

Downloads last month: 995

KoboldAI
/

OPT-6.7B-Nerybus-Mix

OPT-6.7B-Nerybus-Mix

License

Evaluation Results

Spaces using KoboldAI/OPT-6.7B-Nerybus-Mix 35