Instructions to use BeardedMonster/MOE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BeardedMonster/MOE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BeardedMonster/MOE", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BeardedMonster/MOE", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BeardedMonster/MOE with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BeardedMonster/MOE" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeardedMonster/MOE", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/BeardedMonster/MOE
- SGLang
How to use BeardedMonster/MOE 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 "BeardedMonster/MOE" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeardedMonster/MOE", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "BeardedMonster/MOE" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeardedMonster/MOE", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use BeardedMonster/MOE with Docker Model Runner:
docker model run hf.co/BeardedMonster/MOE
| { | |
| "additional_special_tokens": [ | |
| "<|system|>", | |
| "<twi>", | |
| "<fon>", | |
| "<fat>", | |
| "<ewe>", | |
| "<ton>", | |
| "<aka>", | |
| "<toxic>", | |
| "<STR>", | |
| "<text>", | |
| "<intent>", | |
| "<think>", | |
| "</think>", | |
| "<reason>", | |
| "<score>", | |
| "<|user|>", | |
| "<identify>", | |
| "<lang_id>", | |
| "<lang_id_label>", | |
| "<ner>", | |
| "<NER>", | |
| "<summary>", | |
| "<summarize>", | |
| "<|assistant|>", | |
| "<context>", | |
| "<clean>", | |
| "<diacritize>", | |
| "<lang_ID>", | |
| "<lang_ID_label>", | |
| "<title>", | |
| "<headline>", | |
| "<qa>", | |
| "<tool_call>", | |
| "<|edit|>", | |
| "<|data_extract|>", | |
| "<|generate|>", | |
| "<|math|>", | |
| "<|JSON|>", | |
| "<|code|>", | |
| "<|is_technical|>", | |
| "<|input_lang|>", | |
| "<|target_lang|>", | |
| "</tool_call>", | |
| "<|is_legal|>", | |
| "<|is_medical|>", | |
| "<|is_scientific|>", | |
| "<|is_non_technical|>", | |
| "<|is_financial|>", | |
| "<|RAG|>", | |
| "<tool_response>", | |
| "</tool_response>", | |
| "</context>", | |
| "<task_plan>", | |
| "</task_plan>", | |
| "<|plan|>", | |
| "|analyze|>", | |
| "<|recommend|>", | |
| "<|explain|>", | |
| "<|debug|>", | |
| "<|code|>", | |
| "<|chat|>", | |
| "<nli>" | |
| ], | |
| "bos_token": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |