Instructions to use meta-llama/Meta-Llama-3-70B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Meta-Llama-3-70B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3-70B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Meta-Llama-3-70B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Meta-Llama-3-70B-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": "meta-llama/Meta-Llama-3-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Meta-Llama-3-70B-Instruct

SGLang

How to use meta-llama/Meta-Llama-3-70B-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 "meta-llama/Meta-Llama-3-70B-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": "meta-llama/Meta-Llama-3-70B-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 "meta-llama/Meta-Llama-3-70B-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": "meta-llama/Meta-Llama-3-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Meta-Llama-3-70B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Meta-Llama-3-70B-Instruct
```

Error while running for inference

#27

by sumitsoman - opened Apr 23, 2024

Discussion

sumitsoman

Apr 23, 2024

Get this message, any suggestion how to resolve?

2024-04-23T11:39:19.958232Z ERROR batch{batch_size=1}:prefill:prefill{id=2 size=1}:prefill{id=2 size=1}: text_generation_client: router/client/src/lib.rs:33: Server error: max(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.
2024-04-23T11:39:19.959108Z ERROR HTTP request{otel.name=POST /generate http.client_ip= http.flavor=1.1 http.host=129.192.82.77:8080 http.method=POST http.route=/generate http.scheme=HTTP http.target=/generate http.user_agent=python-requests/2.31.0 otel.kind=server trace_id=7a57d270afb6fb24c60310a98d54c704}:generate{parameters=GenerateParameters { best_of: Some(1), temperature: Some(1e-6), repetition_penalty: Some(1.2), top_k: Some(50), top_p: Some(0.95), typical_p: Some(0.95), do_sample: true, max_new_tokens: 2000, return_full_text: Some(true), stop: ["<|endoftext|>"], truncate: Some(1023), watermark: false, details: false, decoder_input_details: false, seed: Some(42), top_n_tokens: Some(1) }}:generate{request=GenerateRequest { inputs: "what is 1+1", parameters: GenerateParameters { best_of: Some(1), temperature: Some(1e-6), repetition_penalty: Some(1.2), top_k: Some(50), top_p: Some(0.95), typical_p: Some(0.95), do_sample: true, max_new_tokens: 2000, return_full_text: Some(true), stop: ["<|endoftext|>"], truncate: Some(1023), watermark: false, details: false, decoder_input_details: false, seed: Some(42), top_n_tokens: Some(1) } }}:generate_stream{request=GenerateRequest { inputs: "what is 1+1", parameters: GenerateParameters { best_of: Some(1), temperature: Some(1e-6), repetition_penalty: Some(1.2), top_k: Some(50), top_p: Some(0.95), typical_p: Some(0.95), do_sample: true, max_new_tokens: 2000, return_full_text: Some(true), stop: ["<|endoftext|>"], truncate: Some(1023), watermark: false, details: false, decoder_input_details: false, seed: Some(42), top_n_tokens: Some(1) } }}:infer:send_error: text_generation_router::infer: router/src/infer.rs:588: Request failed during generation: Server error: max(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.

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