Instructions to use normalcomputing/extended-mind-mpt-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use normalcomputing/extended-mind-mpt-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="normalcomputing/extended-mind-mpt-7b-chat", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("normalcomputing/extended-mind-mpt-7b-chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use normalcomputing/extended-mind-mpt-7b-chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/normalcomputing/extended-mind-mpt-7b-chat

SGLang

How to use normalcomputing/extended-mind-mpt-7b-chat 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 "normalcomputing/extended-mind-mpt-7b-chat" \
    --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": "normalcomputing/extended-mind-mpt-7b-chat",
		"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 "normalcomputing/extended-mind-mpt-7b-chat" \
        --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": "normalcomputing/extended-mind-mpt-7b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use normalcomputing/extended-mind-mpt-7b-chat with Docker Model Runner:
```
docker model run hf.co/normalcomputing/extended-mind-mpt-7b-chat
```

Prompt template?

by Tostino - opened Nov 14, 2023

Discussion

Tostino

Nov 14, 2023

What prompt/chat template was this model trained with?

Are there any plans to implement a chat template for the tokenizer? https://huggingface.co/docs/transformers/main/en/chat_templating

phoebeklett

Nov 14, 2023

This model has not been finetuned, and should be prompted as specified by Mosaic's original documentation.

Tostino

Nov 15, 2023

Got it. Sorry for the confusion, the fact that there was "chat" in the name made me think it was actually fine-tuned for chat.

Tostino changed discussion status to closed Nov 15, 2023

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