Instructions to use flemmingmiguel/MBX-7B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flemmingmiguel/MBX-7B-v3 with Transformers:

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

pipe = pipeline("text-generation", model="flemmingmiguel/MBX-7B-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flemmingmiguel/MBX-7B-v3")
model = AutoModelForCausalLM.from_pretrained("flemmingmiguel/MBX-7B-v3")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flemmingmiguel/MBX-7B-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flemmingmiguel/MBX-7B-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flemmingmiguel/MBX-7B-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flemmingmiguel/MBX-7B-v3

SGLang

How to use flemmingmiguel/MBX-7B-v3 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 "flemmingmiguel/MBX-7B-v3" \
    --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": "flemmingmiguel/MBX-7B-v3",
		"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 "flemmingmiguel/MBX-7B-v3" \
        --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": "flemmingmiguel/MBX-7B-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flemmingmiguel/MBX-7B-v3 with Docker Model Runner:
```
docker model run hf.co/flemmingmiguel/MBX-7B-v3
```

Incorrect model mentioned in merge?

by racinmat - opened Feb 2, 2024

Discussion

racinmat

Feb 2, 2024

Hi, in the readme, you mention that
MBX-7B-v3 is a merge of the following models using LazyMergekit:
flemmingmiguel/MBX-7B
flemmingmiguel/MBX-7B-v3

but this model is flemmingmiguel/MBX-7B-v3, so which models were merged to produce this one?
I see that https://huggingface.co/flemmingmiguel/MBX-7B-v2 has similar typo, stating that:
MBX-7B-v2 is a merge of the following models using LazyMergekit:

flemmingmiguel/MBX-7B
flemmingmiguel/MBX-7B-v2

flemmingmiguel

Owner Feb 23, 2024

Hi, actually the readme is correct there was a previous v3 model that was used in the merge but was deleted from the hub before this one was uploaded, same thing happened with v2

Probably a mistake in naming since v2 and v3 were not actual progressions from one another but 2 different ideas I was testing and this one turned out better, I'll write more about the process sometime soon

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