Instructions to use RDson/Llama-3-Magenta-Instruct-4x8B-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RDson/Llama-3-Magenta-Instruct-4x8B-MoE with Transformers:

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

pipe = pipeline("text-generation", model="RDson/Llama-3-Magenta-Instruct-4x8B-MoE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RDson/Llama-3-Magenta-Instruct-4x8B-MoE")
model = AutoModelForCausalLM.from_pretrained("RDson/Llama-3-Magenta-Instruct-4x8B-MoE", 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 RDson/Llama-3-Magenta-Instruct-4x8B-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RDson/Llama-3-Magenta-Instruct-4x8B-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": "RDson/Llama-3-Magenta-Instruct-4x8B-MoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RDson/Llama-3-Magenta-Instruct-4x8B-MoE

SGLang

How to use RDson/Llama-3-Magenta-Instruct-4x8B-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 "RDson/Llama-3-Magenta-Instruct-4x8B-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": "RDson/Llama-3-Magenta-Instruct-4x8B-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 "RDson/Llama-3-Magenta-Instruct-4x8B-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": "RDson/Llama-3-Magenta-Instruct-4x8B-MoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RDson/Llama-3-Magenta-Instruct-4x8B-MoE with Docker Model Runner:
```
docker model run hf.co/RDson/Llama-3-Magenta-Instruct-4x8B-MoE
```

RDson commited on May 17, 2024

Commit

c83236d

verified ·

1 Parent(s): f0ca4c5

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -6,11 +6,14 @@ tags:
 - llama 3
 - 4x8b
 ---
-<img src="https://i.imgur.com/c1Mv8cy.png" width="640"/>
 # Llama-3-Magenta-Instruct-4x8B-MoE
-GGUF files are available here: [RDson/Llama-3-Magenta-Instruct-4x8B-MoE-GGUF](https://huggingface.co/RDson/Llama-3-Magenta-Instruct-4x8B-MoE-GGUF).
 This is a experimental MoE created from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B), [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) and [Muhammad2003/Llama3-8B-OpenHermes-DPO](https://huggingface.co/Muhammad2003/Llama3-8B-OpenHermes-DPO) using Mergekit.

 - llama 3
 - 4x8b
 ---
 # Llama-3-Magenta-Instruct-4x8B-MoE
+<img src="https://i.imgur.com/c1Mv8cy.png" width="640"/>
+You should also check out the updated [Llama-3-Peach-Instruct-4x8B-MoE](https://huggingface.co/RDson/Llama-3-Peach-Instruct-4x8B-MoE)!
+GGUF files are available here: [Llama-3-Magenta-Instruct-4x8B-MoE-GGUF](https://huggingface.co/RDson/Llama-3-Magenta-Instruct-4x8B-MoE-GGUF).
 This is a experimental MoE created from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B), [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) and [Muhammad2003/Llama3-8B-OpenHermes-DPO](https://huggingface.co/Muhammad2003/Llama3-8B-OpenHermes-DPO) using Mergekit.