README.md

---
language:
- en
pipeline_tag: text-generation
tags:
- cobalt
- 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
- math
- math-instruct
- conversational
- chat
- instruct
model_type: llama
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- sequelbox/Polytope
- LDJnr/Pure-Dove
model-index:
- name: Llama3.1-8B-Cobalt
  results:
  - 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: 71.68
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      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: 27.24
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      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: 15.33
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      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: 4.81
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      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: 4.7
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      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: 29.59
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Cobalt
      name: Open LLM Leaderboard
license: llama3.1
---


Cobalt is a math-instruct model built on Llama 3.1 8b.
- High quality math instruct performance within the Llama 3 Instruct chat format
- Finetuned on synthetic math-instruct data generated with Llama 3.1 405b. [Find the current version of the dataset here!](https://huggingface.co/datasets/sequelbox/Polytope)


## Version

This is the **2024-08-16** release of Cobalt for Llama 3.1 8b.

Help us and recommend Cobalt to your friends! We're excited for more Cobalt releases in the future. 

Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 :)


## Prompting Guide
Cobalt 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:


import transformers
import torch

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

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

messages = [
    {"role": "system", "content": "You are Cobalt, expert math AI."},
    {"role": "user", "content": "I'm buying a $50 shirt and a $80 pair of pants, both currently at a 25% discount. How much will I pay?"}
]

outputs = pipeline(
    messages,
    max_new_tokens=1024,
)

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


## The Model
Cobalt is built on top of Llama 3.1 8b Instruct, using math-instruct data to supplement math-instruct performance using Llama 3.1 Instruct prompt style.

Our current version of the Cobalt math-instruct dataset is [sequelbox/Polytope](https://huggingface.co/datasets/sequelbox/Polytope), supplemented with a small selection of data from [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove) for general chat consistency.


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


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

[Check out our HuggingFace page for Shining Valiant 2 and our other Build Tools models for creators!](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.