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")
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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

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
```

requires Pro

#57

by MatrixIA - opened Jun 20, 2024

Discussion

MatrixIA

Jun 20, 2024

getting this message when doing inference
Server meta-llama/Meta-Llama-3-70B-Instruct does not seem to support chat completion. Error: Model requires a Pro subscription; check out hf.co/pricing to learn more. Make sure to include your HF token in your query.

just yesterday i was testing and it seemed to work (serverless API)

YiyiDane

Jun 23, 2024

I have the same problem too.

YiyiDane

Jun 23, 2024

Token is valid (permission: fineGrained).
Your token has been saved in your configured git credential helpers (manager).
Your token has been saved to C:\Users\Administrator.cache\huggingface\token
Login successful
Server /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FMeta-Llama-3-70B-Instruct%2Fv1%2Fchat%2Fcompletions%3C%2Fa%3E does not seem to support chat completion. Falling back to text generation. Error: (Request ID: k3O10Rur0ON-c9TLe0lGa)

Bad request:
Authorization header is correct, but the token seems invalid
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\utils_errors.py", line 304, in hf_raise_for_status
response.raise_for_status()
File "C:\ProgramData\miniconda3\envs\cuda_env\Lib\site-packages\requests\models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FMeta-Llama-3-70B-Instruct%2Fv1%2Fchat%2Fcompletions%3C%2Fa%3E%3C%2Fp%3E

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 706, in chat_completion
data = self.post(
^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 273, in post
hf_raise_for_status(response)
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\utils_errors.py", line 358, in hf_raise_for_status
raise BadRequestError(message, response=response) from e
huggingface_hub.utils._errors.BadRequestError: (Request ID: k3O10Rur0ON-c9TLe0lGa)

Bad request:
Authorization header is correct, but the token seems invalid

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\utils_errors.py", line 304, in hf_raise_for_status
response.raise_for_status()
File "C:\ProgramData\miniconda3\envs\cuda_env\Lib\site-packages\requests\models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FMeta-Llama-3-70B-Instruct%3C%2Fa%3E%3C%2Fp%3E

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "E:\Python\T5\T5Agent.py", line 37, in
response_content = llm_engine(messages)
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\transformers\agents\llm_engine.py", line 85, in call
response = self.client.chat_completion(messages, stop=stop_sequences, max_tokens=1500)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 738, in chat_completion
return self.chat_completion(
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 770, in chat_completion
text_generation_output = self.text_generation(
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 2061, in text_generation
raise_text_generation_error(e)
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_common.py", line 460, in raise_text_generation_error
raise http_error
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 2032, in text_generation
bytes_output = self.post(json=payload, model=model, task="text-generation", stream=stream) # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\inference_client.py", line 273, in post
hf_raise_for_status(response)
File "C:\Users\Administrator\AppData\Roaming\Python\Python312\site-packages\huggingface_hub\utils_errors.py", line 358, in hf_raise_for_status
raise BadRequestError(message, response=response) from e
huggingface_hub.utils._errors.BadRequestError: (Request ID: vUBetFgYdy5jSneTSQgy4)

Bad request:
Authorization header is correct, but the token seems invalid

geraldschwab

Jul 4, 2024

is this for running the model on the API, or is there a subscription required to run it locally?

m-ric

Jul 5, 2024

@MatrixIA since we started serving this model on our Serverless API, it has been only available to PRO users: I advise you to get the subscription, it's very convenient! 🤗

selvaonline

Sep 20, 2024

i get this error even after i purchase pro membership which is $9 per month. Do i need to get different license for Serverless API?

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