Instructions to use jsfs11/MixtureofMerges-MoE-4x7b-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsfs11/MixtureofMerges-MoE-4x7b-v4 with Transformers:

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

pipe = pipeline("text-generation", model="jsfs11/MixtureofMerges-MoE-4x7b-v4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsfs11/MixtureofMerges-MoE-4x7b-v4")
model = AutoModelForCausalLM.from_pretrained("jsfs11/MixtureofMerges-MoE-4x7b-v4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jsfs11/MixtureofMerges-MoE-4x7b-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsfs11/MixtureofMerges-MoE-4x7b-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsfs11/MixtureofMerges-MoE-4x7b-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jsfs11/MixtureofMerges-MoE-4x7b-v4

SGLang

How to use jsfs11/MixtureofMerges-MoE-4x7b-v4 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 "jsfs11/MixtureofMerges-MoE-4x7b-v4" \
    --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": "jsfs11/MixtureofMerges-MoE-4x7b-v4",
		"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 "jsfs11/MixtureofMerges-MoE-4x7b-v4" \
        --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": "jsfs11/MixtureofMerges-MoE-4x7b-v4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jsfs11/MixtureofMerges-MoE-4x7b-v4 with Docker Model Runner:
```
docker model run hf.co/jsfs11/MixtureofMerges-MoE-4x7b-v4
```

GGUF

by Ttimofeyka - opened Feb 23, 2024

Discussion

Ttimofeyka

Feb 23, 2024

Can you publish GGUF-quantized files? I see them in your profile for older versions, but not for the latest one.

jsfs11

Owner Feb 24, 2024

Yeah no worries - just finished 🙂, just wasn't sure if anyone was interested in them.

jsfs11 changed discussion status to closed Feb 24, 2024

Ttimofeyka

Feb 24, 2024

In theory, according to benchmarks, this is about the best 4x7B model for chat (RP).

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