Instructions to use gagan3012/MetaModel_moe_multilingualv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gagan3012/MetaModel_moe_multilingualv2 with Transformers:

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

pipe = pipeline("text-generation", model="gagan3012/MetaModel_moe_multilingualv2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gagan3012/MetaModel_moe_multilingualv2")
model = AutoModelForCausalLM.from_pretrained("gagan3012/MetaModel_moe_multilingualv2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gagan3012/MetaModel_moe_multilingualv2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gagan3012/MetaModel_moe_multilingualv2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gagan3012/MetaModel_moe_multilingualv2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gagan3012/MetaModel_moe_multilingualv2

SGLang

How to use gagan3012/MetaModel_moe_multilingualv2 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 "gagan3012/MetaModel_moe_multilingualv2" \
    --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": "gagan3012/MetaModel_moe_multilingualv2",
		"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 "gagan3012/MetaModel_moe_multilingualv2" \
        --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": "gagan3012/MetaModel_moe_multilingualv2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gagan3012/MetaModel_moe_multilingualv2 with Docker Model Runner:
```
docker model run hf.co/gagan3012/MetaModel_moe_multilingualv2
```

MetaModel_moe_multilingualv2 / mergekit_moe_config.yml

gagan3012

Upload folder using huggingface_hub

7271349 over 2 years ago

Raw

History Blame Contribute Delete

1.21 kB

	base_model: mlabonne/NeuralMarcoro14-7B
	gate_mode: hidden
	dtype: bfloat16
	experts:
	- source_model: openchat/openchat-3.5-1210
	positive_prompts:
	- "chat"
	- "assistant"
	- "tell me"
	- "explain"
	- source_model: beowolx/CodeNinja-1.0-OpenChat-7B
	positive_prompts:
	- "code"
	- "python"
	- "javascript"
	- "programming"
	- "algorithm"
	- source_model: maywell/PiVoT-0.1-Starling-LM-RP
	positive_prompts:
	- "storywriting"
	- "write"
	- "scene"
	- "story"
	- "character"
	- source_model: WizardLM/WizardMath-7B-V1.1
	positive_prompts:
	- "reason"
	- "math"
	- "mathematics"
	- "solve"
	- "count"
	- source_model: davidkim205/komt-mistral-7b-v1
	positive_prompts:
	- "korean"
	- "answer in korean"
	- "korea"
	- source_model: OpenBuddy/openbuddy-zephyr-7b-v14.1
	positive_prompts:
	- "chinese"
	- "china"
	- "answer in chinese"
	- source_model: manishiitg/open-aditi-hi-v1
	positive_prompts:
	- "hindi"
	- "india"
	- "hindu"
	- "answer in hindi"
	- source_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
	positive_prompts:
	- "german"
	- "germany"
	- "answer in german"
	- "deutsch"