---

language:
- en
pipeline_tag: text-generation
tags:
- esper
- esper-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
- code
- code-instruct
- python
- dev-ops
- terraform
- azure
- aws
- gcp
- architect
- engineer
- developer
- conversational
- chat
- instruct
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- sequelbox/Titanium
- sequelbox/Tachibana
- sequelbox/Supernova
model_type: llama
model-index:
- name: ValiantLabs/Llama3.1-8B-Esper2
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-Shot)
      type: Winogrande
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 75.85
      name: acc
license: llama3.1

---

[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)


# QuantFactory/Llama3.1-8B-Esper2-GGUF
This is quantized version of [ValiantLabs/Llama3.1-8B-Esper2](https://huggingface.co/ValiantLabs/Llama3.1-8B-Esper2) created using llama.cpp

# Original Model Card



![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/4I6oK8DG0so4VD8GroFsd.jpeg)


Esper 2 is a DevOps and cloud architecture code specialist built on Llama 3.1 8b.
- Expertise-driven, an AI assistant focused on AWS, Azure, GCP, Terraform, Dockerfiles, pipelines, shell scripts and more!
- Real world problem solving and high quality code instruct performance within the Llama 3.1 Instruct chat format
- Finetuned on synthetic [DevOps-instruct](https://huggingface.co/datasets/sequelbox/Titanium) and [code-instruct](https://huggingface.co/datasets/sequelbox/Tachibana) data generated with Llama 3.1 405b.
- Overall chat performance supplemented with [generalist chat data.](https://huggingface.co/datasets/sequelbox/Supernova)

Try our code-instruct AI assistant [Enigma!](https://huggingface.co/ValiantLabs/Llama3.1-8B-Enigma)


## Version

This is the **2024-10-02** release of Esper 2 for Llama 3.1 8b.

Esper 2 is now available for [Llama 3.2 3b!](https://huggingface.co/ValiantLabs/Llama3.2-3B-Esper2)

Esper 2 will be coming to more model sizes soon :)


## Prompting Guide
Esper 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-Esper2"

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

messages = [
    {"role": "system", "content": "You are an AI assistant."},
    {"role": "user", "content": "Hi, how do I optimize the size of a Docker image?"}
]

outputs = pipeline(
    messages,
    max_new_tokens=2048,
)

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

## The Model
Esper 2 is built on top of Llama 3.1 8b Instruct, improving performance through high quality DevOps, code, and chat data in Llama 3.1 Instruct prompt style.

Our current version of Esper 2 is trained on DevOps data from [sequelbox/Titanium](https://huggingface.co/datasets/sequelbox/Titanium), supplemented by code-instruct data from [sequelbox/Tachibana](https://huggingface.co/datasets/sequelbox/Tachibana) and general chat data from [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)


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


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

[Check out our HuggingFace page for Shining Valiant 2  Enigma, 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.