Instructions to use OccamRazor/mpt-7b-storywriter-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OccamRazor/mpt-7b-storywriter-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="OccamRazor/mpt-7b-storywriter-4bit-128g", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OccamRazor/mpt-7b-storywriter-4bit-128g", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OccamRazor/mpt-7b-storywriter-4bit-128g", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OccamRazor/mpt-7b-storywriter-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OccamRazor/mpt-7b-storywriter-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OccamRazor/mpt-7b-storywriter-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OccamRazor/mpt-7b-storywriter-4bit-128g

SGLang

How to use OccamRazor/mpt-7b-storywriter-4bit-128g 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 "OccamRazor/mpt-7b-storywriter-4bit-128g" \
    --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": "OccamRazor/mpt-7b-storywriter-4bit-128g",
		"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 "OccamRazor/mpt-7b-storywriter-4bit-128g" \
        --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": "OccamRazor/mpt-7b-storywriter-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OccamRazor/mpt-7b-storywriter-4bit-128g with Docker Model Runner:
```
docker model run hf.co/OccamRazor/mpt-7b-storywriter-4bit-128g
```

0cc4m/koboldAI: expected scalar type BFloat16 but found Half

by fawogin598 - opened Jul 26, 2023

Discussion

fawogin598

Jul 26, 2023

Using your fork locally, this model throws the error expected scalar type BFloat16 but found Half
IDK what to do to fix this.
Would you please let me know if it works for you?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment