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

Libraries

How to use TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge with Transformers:

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

pipe = pipeline("text-generation", model="TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge")
model = AutoModelForCausalLM.from_pretrained("TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-Merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge

SGLang

How to use TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-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_Storywriter-Pythia_ChatBase-Merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge with Docker Model Runner:
```
docker model run hf.co/TehVenom/MPT-7b_Storywriter-Pythia_ChatBase-Merge
```

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

Check out the documentation for more information.

The models have been hacked together because their base weights share a similar architecture. But for now using the Pythia inference code only gibberish is generated, while when trying to use the MPT based inference code, i am running into errors that stop it from working.

Currently trying to adapt the "MPT-7b Storywriter 65k" based inference code to work with this new model merge. I'd appreciate tips if anyone tries their hand at it.

This model is not functional as is.

Downloads last month: 11