Instructions to use ValiantLabs/Llama2-70B-ShiningValiant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ValiantLabs/Llama2-70B-ShiningValiant with Transformers:

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

pipe = pipeline("text-generation", model="ValiantLabs/Llama2-70B-ShiningValiant")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ValiantLabs/Llama2-70B-ShiningValiant")
model = AutoModelForCausalLM.from_pretrained("ValiantLabs/Llama2-70B-ShiningValiant")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ValiantLabs/Llama2-70B-ShiningValiant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ValiantLabs/Llama2-70B-ShiningValiant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/Llama2-70B-ShiningValiant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ValiantLabs/Llama2-70B-ShiningValiant

SGLang

How to use ValiantLabs/Llama2-70B-ShiningValiant 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/Llama2-70B-ShiningValiant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/Llama2-70B-ShiningValiant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/Llama2-70B-ShiningValiant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/Llama2-70B-ShiningValiant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ValiantLabs/Llama2-70B-ShiningValiant with Docker Model Runner:
```
docker model run hf.co/ValiantLabs/Llama2-70B-ShiningValiant
```
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!

Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendliness.

Uses the llama-2-70b-chat model, with safetensors
Finetuned on multiple runs across private and public data
Data focused on knowledge, enthusiasm, and structured reasoning
Our new release features greatly expanded personality capability, bringing a more immersive chat experience

Version

The current version is 1.4! We've greatly expanded our personality dataset and fixed some bugs to deliver our strongest real-chat experience so far.

(We're also exploring new models and architectures, to deliver helpful open source capabilities for users and creators!)

Previous versions remain available in the repository. New models will be released for everyone once our team's training and validation process is complete.

Evaluation

Version 1.4 is awaiting results from the Open LLM leaderboard.

Prompting Guide

Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts! A few examples of different formats:

[INST] Good morning! Can you let me know how to parse a text file and turn the semicolons into commas? [/INST]
[INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
[INST] << SYS >>You are an intelligent, helpful AI assistant.<< /SYS >>Deep dive about a country with interesting history: [/INST]

The Model

Shining Valiant is built on top of Spell Blade, which uses Llama 2's 70b parameter architecture and features upgraded general and chat capability.

Our private data focuses primarily on applying Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!

With this release, the personality component of our Shining Valiant dataset has been greatly improved. We're excited to use it in future releases of this model and others.