README.md

---
language:
- en
pipeline_tag: text-generation
tags:
- shining-valiant
- shining-valiant-2
- valiant
- valiant-labs
- llama
- llama-3.1
- llama-3.1-instruct
- llama-3.1-instruct-8b
- llama-3
- llama-3-instruct
- llama-3-instruct-8b
- 8b
- science
- physics
- biology
- chemistry
- compsci
- computer-science
- engineering
- technical
- conversational
- chat
- instruct
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- sequelbox/Celestia
- sequelbox/Supernova
model_type: llama
model-index:
- name: Llama3.1-8B-ShiningValiant2
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-Shot)
      type: Winogrande
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 77.35
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU College Biology (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 76.39
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU High School Biology (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 79.03
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU College Chemistry (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 50.0
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU High School Chemistry (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 53.2
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU College Physics (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 43.14
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU High School Physics (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 42.38
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU College Computer Science (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 55.0
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU High School Computer Science (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 66.0
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU STEM (5-Shot)
      type: MMLU
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 55.57
      name: acc
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 65.24
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 26.35
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 11.63
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 8.95
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 7.19
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 26.38
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
      name: Open LLM Leaderboard
license: llama3.1
---


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/EXX7TKbB-R6arxww2mk0R.jpeg)


Shining Valiant 2 is a chat model built on Llama 3.1 8b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
  - Finetuned on [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) for best available general performance
  - Trained on a variety of our high quality open source data; focused on science, engineering, technical knowledge, and structured reasoning
  - Also available for [Llama 3.1 70b](https://huggingface.co/ValiantLabs/Llama3.1-70B-ShiningValiant2) and [Llama 3.2 3b!](https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2)


## Version

This is the **2024-09-16** release of Shining Valiant 2 for Llama 3.1 8b.

We've improved and open-sourced our new baseline [science-instruct dataset](https://huggingface.co/datasets/sequelbox/Celestia). This release features improvements in physics, chemistry, biology, and computer science.

Future upgrades will continue to expand Shining Valiant's technical knowledge base.

Help us and recommend Shining Valiant 2 to your friends!


## Prompting Guide
Shining Valiant 2 uses the [Llama 3.1 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) prompt format. The example script below can be used as a starting point for general chat:

```python
import transformers
import torch

model_id = "ValiantLabs/Llama3.1-8B-ShiningValiant2"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are Shining Valiant, a highly capable chat AI."},
    {"role": "user", "content": "Describe the role of transformation matrices in 3D graphics."}
]

outputs = pipeline(
    messages,
    max_new_tokens=2048,
)

print(outputs[0]["generated_text"][-1])
```


## The Model
Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.

The current version of Shining Valiant 2 is trained on technical knowledge using [sequelbox/Celestia](https://huggingface.co/datasets/sequelbox/Celestia) and general chat capability using [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)

Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical. (As a general note: we're hoping to replace and open-source this part of Shining Valiant's dataset with synthetic data soon!)


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)


Shining Valiant 2 is created by [Valiant Labs.](http://valiantlabs.ca/)

[Check out our HuggingFace page for our open-source Build Tools models, including the newest version of code-specialist Enigma!](https://huggingface.co/ValiantLabs)

[Follow us on X for updates on our models!](https://twitter.com/valiant_labs)

We care about open source.
For everyone to use.

We encourage others to finetune further from our models.