---
language:
- en
pipeline_tag: text-generation
tags:
- fireplace
- valiant
- valiant-labs
- llama
- llama-3
- llama-3-instruct
- llama-3-instruct-70b
- 70b
- function-calling
- conversational
- chat
- instruct
model_type: llama
license: llama3
---


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


Fireplace is a function-calling model for Llama 3 70b Instruct.
  - combines function-calling abilities with a high-performance, versatile chat model
  - function-calling utilizing the Llama 3 Instruct format

This version of Fireplace, like our previous [Fireplace-13b](https://huggingface.co/ValiantLabs/Fireplace-13b) and [Fireplace-34b](https://huggingface.co/ValiantLabs/Fireplace-34b) models, focuses on combining chat-instruct and function-calling only.

**We're working now on Fireplace 2 for Llama 3**, which will include function calling as one of **several enhanced technical skills**.

## Version

This is the **2024-05-09** release of Fireplace for Llama 3 70b.

We're excited to bring additional releases for Fireplace and other models in our Build Tools lineup to Llama 3 soon!

## Prompting Guide
Fireplace uses the [Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) prompt format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>

Example input for function calling:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n You are Fireplace, an expert code assistant with access to the following functions. Use them if required - { "name": "calculate_tip", "description": "Calculate the tip amount for a bill", "parameters": { "type": "object", "properties": { "bill_amount": { "type": "number", "description": "The total amount of the bill" }, "tip_percentage": { "type": "number", "description": "The percentage of tip to be given" } }, "required": [ "bill_amount", "tip_percentage" ] } } { "name": "check_website_availability", "description": "Check the availability of a website", "parameters": { "type": "object", "properties": { "url": { "type": "string", "description": "The URL of the website" } }, "required": [ "url" ] } } <|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHi, I need help with calculating a tip. My bill is $100 and I want to leave a 30% tip. <|eot_id|><|start_header_id|>assistant<|end_header_id|>

For assistant handling of function responses, deliver them in a new user message:

<|start_header_id|>user<|end_header_id|>\n\n FUNCTION RESPONSE: {"status": "success", "message": "Email has been sent successfully"} <|eot_id|>

## WARNING: text-generation-webui

When using Llama 3 Instruct models (including Fireplace) with [text-generation-webui](https://github.com/oobabooga/text-generation-webui/tree/main) note that a current bug in webui can result in incorrect reading of the model's ending tokens, causing unfinished outputs and incorrect structure.

For a [temporary workaround](https://github.com/oobabooga/text-generation-webui/issues/5885) if you encounter this issue, edit Fireplace's tokenizer_config file as indicated:

from "eos_token": "<|end_of_text|>",

to "eos_token": "<|eot_id|>",

## The Model
Fireplace is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.

This version of Fireplace uses the [glaiveai/glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2) dataset converted to Llama 3 Instruct format.



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


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

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