|
--- |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- fireplace |
|
- valiant |
|
- valiant-labs |
|
- llama |
|
- llama-2 |
|
- llama-2-chat |
|
- 13b |
|
model_type: llama |
|
license: apache-2.0 |
|
--- |
|
|
|
|
|
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. |
|
|
|
(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 **1.0** 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. We're excitedly working on our next open source models now! |
|
|
|
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 taken from [the training dataset](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2). Assistant can make function calls, which are given between <functioncall> and <|endoftext|>: |
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
(Please note that <|endoftext|> is not an EOS/EOT token, it is used to indicate the end of an 'ASSISTANT: ' response in the training data. Post-processing should be used to extract the function response as required by the user.) |
|
|
|
For handling of function call responses, append "FUNCTION RESPONSE: " to the existing chat history: |
|
|
|
|
|
|
|
 |
|
|
|
|
|
 |
|
|
|
|
|
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. |
|
|
|
|
|
 |
|
|
|
|
|
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. |
