sequelbox commited on
Commit
f867b9d
·
verified ·
1 Parent(s): afbecb4

model card

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -120,17 +120,18 @@ model-index:
120
 
121
  Fireplace is a function-calling model for Llama 3 70b Instruct.
122
  - combines function-calling abilities with a high-performance, versatile chat model
123
- - function-calling utilizing the Llama 3 Instruct format
124
 
125
- 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.
126
 
127
- **We're working now on Fireplace 2 for Llama 3**, which will include function calling as one of **several enhanced technical skills**.
 
128
 
129
  ## Version
130
 
131
  This is the **2024-05-09** release of Fireplace for Llama 3 70b.
132
 
133
- We're excited to bring additional releases for Fireplace and other models in our Build Tools lineup to Llama 3 soon!
134
 
135
  ## Prompting Guide
136
  Fireplace uses the [Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) prompt format:
 
120
 
121
  Fireplace is a function-calling model for Llama 3 70b Instruct.
122
  - combines function-calling abilities with a high-performance, versatile chat model
123
+ - system message function-calling utilizing the Llama 3 Instruct format
124
 
125
+ This version of Fireplace focuses on combining chat-instruct and system-message function-calling only.
126
 
127
+ **We've just released Fireplace 2 for Llama 3.1 8b**, which includes inline function calls as one of several technical skills (including JSON, SQL, and more!)
128
+ [Try it today!]()
129
 
130
  ## Version
131
 
132
  This is the **2024-05-09** release of Fireplace for Llama 3 70b.
133
 
134
+ We've also released Fireplace 2 for Llama 3.1 8b and we're working on more Fireplace releases to come :)
135
 
136
  ## Prompting Guide
137
  Fireplace uses the [Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) prompt format: