README.md

---
language:
- en
pipeline_tag: text-generation
tags:
- fireplace
- function-calling
- code
- code-instruct
- valiant
- valiant-labs
- llama
- llama-2
- llama-2-chat
- 13b
model_type: llama
license: apache-2.0
---


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/qg49GOlx8zogDOrMTnb89.jpeg)


Fireplace-13b is a function calling model built on the Llama 2 architecture.
  - Built on llama-2-13b architecture, using [CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) as the base model.
  - Emphasizes function calling and code-instruct as skills.
  - Version 1.1 improves output structure for a superior user experience.

(If you're looking for a friendly general-purpose chat model, try ours: [llama-13b](https://huggingface.co/ValiantLabs/ShiningValiantXS) and [70b](https://huggingface.co/ValiantLabs/ShiningValiant))

## Version

This is Version **1.1** of Fireplace-13b. 

The current version of Fireplace-13b uses [CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) trained on [glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2).

Fireplace is the first release in our Build Tools campaign, to deliver helpful open source capabilities for users and creators.

**The next release in our Build Tools series will be coming soon, with an initial release at 70b parameters** - we're very excited to bring this to everyone!

We're also working to bring Fireplace to larger model architectures, to maximize baseline model capability and function-calling performance.

## Prompting Guide
Fireplace-13b specializes in function calling and code instruct/chat. 

See [CodeLlama-13b-Instruct-hf](codellama/CodeLlama-13b-Instruct-hf) for code capabilities of the base model.

For function calling in this version of the model, the recommended format is to deliver the function(s) in a system message and then proceed with chat:

SYSTEM: You are Fireplace, an expert code assistant with access to the following functions. Use them if required -
{
    ""name"": ""function_name"",
}

USER: Can you (do thing from function)?

ASSISTANT: 

Assistant will deliver function call responses between \<functioncall> and <|endoftext|>: 


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/rpfkQKAS0E3483Qxn1HIF.png)


(Please note that <|endoftext|> is not an EOS/EOT token, it is used to indicate the end of function call responses specifically.)

For handling of function call responses, append "FUNCTION RESPONSE: " to the existing chat history:


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/2bKX9Zsk6pHJxKYqEprcq.png)


Fireplace is optimized for function/code capabilities and not general chat, but it has also been trained to utilize general instruct-chat capabilities:


SYSTEM: You are a helpful assistant.

USER: user chat input

ASSISTANT: 


The model may be subject to errors and limitations, including those of the base model and dataset. We offer Fireplace-13b as open source for all to use. The user is responsible for all outputs.


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


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

Try our flagship chat model, [Shining Valiant!](https://huggingface.co/ValiantLabs/ShiningValiant)

[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.