Instructions to use cloudyu/Yi-34Bx2-MoE-60B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudyu/Yi-34Bx2-MoE-60B with Transformers:

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

pipe = pipeline("text-generation", model="cloudyu/Yi-34Bx2-MoE-60B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cloudyu/Yi-34Bx2-MoE-60B")
model = AutoModelForCausalLM.from_pretrained("cloudyu/Yi-34Bx2-MoE-60B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cloudyu/Yi-34Bx2-MoE-60B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cloudyu/Yi-34Bx2-MoE-60B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/Yi-34Bx2-MoE-60B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cloudyu/Yi-34Bx2-MoE-60B

SGLang

How to use cloudyu/Yi-34Bx2-MoE-60B 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 "cloudyu/Yi-34Bx2-MoE-60B" \
    --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": "cloudyu/Yi-34Bx2-MoE-60B",
		"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 "cloudyu/Yi-34Bx2-MoE-60B" \
        --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": "cloudyu/Yi-34Bx2-MoE-60B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cloudyu/Yi-34Bx2-MoE-60B with Docker Model Runner:
```
docker model run hf.co/cloudyu/Yi-34Bx2-MoE-60B
```

Perfect MoE's my write up, and help to you for making MoE's

by rombodawg - opened Jan 14, 2024

Discussion

rombodawg

Jan 14, 2024

Ive created a write up google doc for perfecting the formula for creating MoE models using mergkit. You can find it in the link bellow, Im calling the community (at the very least the people who intend to create models) to read it, use the knowledge to experiment and come back and leave comments on the write up doc for the whole community to share the knowledge and improve our ability to create better ai merged and MoE models.

https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing

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