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

Libraries

How to use OpenPipe/Llama-3.1-70B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="OpenPipe/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("OpenPipe/Llama-3.1-70B-Instruct")
model = AutoModelForCausalLM.from_pretrained("OpenPipe/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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

docker model run hf.co/OpenPipe/Llama-3.1-70B-Instruct

SGLang

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

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

kovsbo commited on Apr 9

Commit

f8df8fa

verified ·

1 Parent(s): 4035a71

Upload openpipe_llama_dual.py

Browse files

Files changed (1) hide show

openpipe_llama_dual.py +4 -3

openpipe_llama_dual.py CHANGED Viewed

@@ -27,9 +27,10 @@ class OpenPipeLlamaDualParser(ToolParser):
     VARIANT_PIPELINE3 = "pipeline3"
     VARIANT_OFFICIAL = "official"
-    def __init__(self, tokenizer: TokenizerLike):
-        super().__init__(tokenizer)
         self.tokenizer = tokenizer
     def _get_template_variant(self, request: ChatCompletionRequest) -> Optional[str]:
         kwargs = getattr(request, "chat_template_kwargs", None)
@@ -261,4 +262,4 @@ class OpenPipeLlamaDualParser(ToolParser):
             tools_called=False,
             tool_calls=[],
             content=model_output,
-        )

     VARIANT_PIPELINE3 = "pipeline3"
     VARIANT_OFFICIAL = "official"
+    def __init__(self, tokenizer: TokenizerLike, tools):
+        super().__init__(tokenizer, tools)
         self.tokenizer = tokenizer
+        self.tools = tools
     def _get_template_variant(self, request: ChatCompletionRequest) -> Optional[str]:
         kwargs = getattr(request, "chat_template_kwargs", None)
             tools_called=False,
             tool_calls=[],
             content=model_output,
+        )