Instructions to use SillyTilly/Meta-Llama-3.1-405B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SillyTilly/Meta-Llama-3.1-405B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SillyTilly/Meta-Llama-3.1-405B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SillyTilly/Meta-Llama-3.1-405B-Instruct")
model = AutoModelForCausalLM.from_pretrained("SillyTilly/Meta-Llama-3.1-405B-Instruct")
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

vLLM

How to use SillyTilly/Meta-Llama-3.1-405B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SillyTilly/Meta-Llama-3.1-405B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SillyTilly/Meta-Llama-3.1-405B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SillyTilly/Meta-Llama-3.1-405B-Instruct

SGLang

How to use SillyTilly/Meta-Llama-3.1-405B-Instruct 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 "SillyTilly/Meta-Llama-3.1-405B-Instruct" \
    --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": "SillyTilly/Meta-Llama-3.1-405B-Instruct",
		"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 "SillyTilly/Meta-Llama-3.1-405B-Instruct" \
        --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": "SillyTilly/Meta-Llama-3.1-405B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SillyTilly/Meta-Llama-3.1-405B-Instruct with Docker Model Runner:
```
docker model run hf.co/SillyTilly/Meta-Llama-3.1-405B-Instruct
```

Concerns

by ChuckMcSneed - opened Aug 5, 2024

Discussion

ChuckMcSneed

Aug 5, 2024

Please tell me it's an outdated/fake model. It can't be real. No way. It's so... lame. There is no wow that I expected from this model.

lucyknada

SillyTilly org Aug 6, 2024

llama 4 will be better, trvst.

lucyknada changed discussion status to closed Aug 6, 2024

NyxKrage

SillyTilly org Aug 6, 2024

jeiku

SillyTilly org Aug 6, 2024

Be the change you wish to see in the world.

deleted

Aug 6, 2024

•

edited Aug 6, 2024

It's clowari da for Meta, BUT FEAR NOT! FOR TEKKY WEKKY AND UWUNOUS RESEARCH WILL FINETUNE L3 405B INTO THE BEST MODEL EVER. TOTAL NOUS VICTORY, TOTAL META DEATH

ChuckMcSneed

Aug 6, 2024

So it is real? Damn. Hopefully it's like llama2 where base is fine, but the official tune sucks.

ChuckMcSneed

Aug 17, 2024

It's clowari da for Meta, BUT FEAR NOT! FOR TEKKY WEKKY AND UWUNOUS RESEARCH WILL FINETUNE L3 405B INTO THE BEST MODEL EVER. TOTAL NOUS VICTORY, TOTAL META DEATH

New 405 hermes is less bad than the official tune, you were right. I started losing hope when I tried Tess 405b, but Hermes didn't disappoint. Total Nous Victory indeed.

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