Instructions to use Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Efficient-Large-Model/Meta-Llama-3.1-70B-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Efficient-Large-Model/Meta-Llama-3.1-70B-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": "Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct

SGLang

How to use Efficient-Large-Model/Meta-Llama-3.1-70B-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 "Efficient-Large-Model/Meta-Llama-3.1-70B-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": "Efficient-Large-Model/Meta-Llama-3.1-70B-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 "Efficient-Large-Model/Meta-Llama-3.1-70B-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": "Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct with Docker Model Runner:
```
docker model run hf.co/Efficient-Large-Model/Meta-Llama-3.1-70B-Instruct
```

Ligeng-Zhu commited on Jul 25, 2024

Commit

29e6dd8

verified ·

1 Parent(s): 5425bcb

Upload files with huggingface_hub

Browse files

Upload model-00007-of-00030.safetensors
Upload model-00013-of-00030.safetensors
Upload model-00020-of-00030.safetensors
Upload model-00028-of-00030.safetensors
Upload model-00018-of-00030.safetensors
Upload model-00015-of-00030.safetensors
Upload model-00006-of-00030.safetensors
Upload model-00008-of-00030.safetensors

Files changed (8) hide show

model-00006-of-00030.safetensors +3 -0
model-00007-of-00030.safetensors +3 -0
model-00008-of-00030.safetensors +3 -0
model-00013-of-00030.safetensors +3 -0
model-00015-of-00030.safetensors +3 -0
model-00018-of-00030.safetensors +3 -0
model-00020-of-00030.safetensors +3 -0
model-00028-of-00030.safetensors +3 -0

model-00006-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:348cd98f65a4b29af25330445841428a9a16e41569c067e63b7f44af9ea19329
+size 4664167408

model-00007-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e52303706b73fca20c1f4137dcdd16929487b432b805d32e6a0a4967d518d2
+size 4664167408

model-00008-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6240b8784a4236a01656e9af27d09b122417ee83eb2d1a35e46f31456230059f
+size 4999711728

model-00013-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:18d9997b7062b00f7b81b9b58f9b684cdbc4368c7d57d14b593be66f6af4a8ce
+size 4999711728

model-00015-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1808b365e913e1370dce52bf05af99e8bbc5f98a74388534be35b18929a96d
+size 4664134408

model-00018-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:538c62f520e233931bc01ae177279d6b97b30642e959e0fd5c78bfdef25833a9
+size 4999711728

model-00020-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8f2458bad38f36b78fe3838f99557f7f6fdc33c33ba993e358c306dd142fa3
+size 4664134408

model-00028-of-00030.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:031f4e3f72548c41f382ae155605729f7a05359b24721ee99da6893939f78cbe
+size 4999711728