Instructions to use TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge with Transformers:

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

pipe = pipeline("text-generation", model="TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge

SGLang

How to use TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge 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 "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge" \
    --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": "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge",
		"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 "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge" \
        --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": "TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge with Docker Model Runner:
```
docker model run hf.co/TehVenom/MPT-7b-InstructAndStorywriting-50_50-Merge
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MPT-7b-InstructAndStorywriting-50_50-Merge

A merge between the long context Storywriting and the short context instruct MPT-7b models.

Model Details:

This model is a merge between the following two MPT-7b models:

2048 CTX MTP-7b Instruct: https://huggingface.co/TehVenom/MPT-7b-instruct-V
65k CTX MTP-7b Storywriter: https://huggingface.co/TehVenom/MPT-7b-storywriter-Apache-2.0/

This merge was done using an weighted average merge strategy, and the end result is a model composed of:

MTP-7b Storywriter [50%] + MTP-7b Instruct [50%]

This was done under for the sake of testing the theory of how long context tunes affect attention when merged with a model that has been trained for a different purpose, on a shorter context span.

The end result is intended to be model that is capable of long prose while inheriting some of the Instruct base's Assistant / Instruct / Helpful properties.

Due to the influence of MPT-7b Storywriter, this model may generate content that is considered NSFW due to the wide array of books sampled for MPT-7b Storywriter.

The specific prompting is unknown, but try approaching it as a story / text completion prompt style first, then a mix of that and Alpaca's instruct format to see what brings most interesting results.

Read the original model card to understand how to run inference on this model.

Downloads last month: 812