Instructions to use ValiantLabs/Llama3-70B-ShiningValiant2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ValiantLabs/Llama3-70B-ShiningValiant2 with Transformers:

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

pipe = pipeline("text-generation", model="ValiantLabs/Llama3-70B-ShiningValiant2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ValiantLabs/Llama3-70B-ShiningValiant2")
model = AutoModelForCausalLM.from_pretrained("ValiantLabs/Llama3-70B-ShiningValiant2")
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 ValiantLabs/Llama3-70B-ShiningValiant2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ValiantLabs/Llama3-70B-ShiningValiant2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/Llama3-70B-ShiningValiant2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ValiantLabs/Llama3-70B-ShiningValiant2

SGLang

How to use ValiantLabs/Llama3-70B-ShiningValiant2 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 "ValiantLabs/Llama3-70B-ShiningValiant2" \
    --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": "ValiantLabs/Llama3-70B-ShiningValiant2",
		"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 "ValiantLabs/Llama3-70B-ShiningValiant2" \
        --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": "ValiantLabs/Llama3-70B-ShiningValiant2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ValiantLabs/Llama3-70B-ShiningValiant2 with Docker Model Runner:
```
docker model run hf.co/ValiantLabs/Llama3-70B-ShiningValiant2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model is legacy - we recommend Shining Valiant 2 for Llama 3.1 70b!

Click here to support our open-source dataset and model releases!

Shining Valiant 2 is a chat model built on Llama 3 70b, finetuned on our data for friendship, insight, knowledge and enthusiasm.

Finetuned on meta-llama/Meta-Llama-3-70B-Instruct for best available general performance
Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning

Version

This is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b.

We're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!

Prompting Guide

Shining Valiant 2 uses the Llama 3 Instruct prompt format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>

Example input:

WARNING: text-generation-webui

When using Llama 3 Instruct models (including Shining Valiant 2) with text-generation-webui note that a current bug in webui can result in incorrect reading of the model's ending tokens, causing unfinished outputs and incorrect structure.

For a temporary workaround if you encounter this issue, edit Shining Valiant 2's tokenizer_config file as indicated:

from "eos_token": "<|end_of_text|>",

to "eos_token": "<|eot_id|>",

The Model

Shining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.

Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!