Matter 7B (Mistral 7B Finetune) - DPO
Matter 7B is contunied full-finetuned on the slim-C version of the Matter dataset, which is curated from over 35 datsets analyzing >6B tokens
Training
It took ~17 hours to train 3 epochs on 4x A100s (80GB) using Axolotl for a full-finetune
Prompt format: This model uses ChatML prompt format.
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Function Calling
Model also supports function calling. Additional tokens for function calling
Model function call tokens
- <|begin_func|> - Function call start token
- <|end_func|> - Function call end token
Function call response tokens
- <|begin_func_response|> - Function response start token
- <|end_func_response|> - Function response end token
Example
<|im_start|>system
You are a helpful assistant with access to the following functions. Use them if required -
{ "name": "get_news_headlines",
"description": "Get the latest news headlines",
"parameters":
{ "type": "object",
"properties":
{ "country":
{ "type": "string",
"description": "The country for which to fetch news"
}
},
"required": [ "country" ]
}
}
<|im_end|>
<|im_start|>user
Can you tell me the latest news headlines for the United States?<|im_end|>
<|im_start|>assistant
<|begin_func|>{"name": "get_news_headlines", "arguments": '{"country": "United States"}'}<|end_func|><|im_end|>
<|im_start|>user
<|begin_func_response|>{
"headlines":
[
"Biden announces new vaccine mandates",
"Hurricane Ida devastates Louisiana",
"Apple unveils new iPhone",
"NASA's Perseverance rover collects first Mars rock sample"
]
}<|end_func_response|>
<|im_end|>
<|im_start|>assistant
Here are the latest news headlines for the United States:
1. Biden announces new vaccine mandates
2. Hurricane Ida devastates Louisiana
3. Apple unveils new iPhone
4. NASA's Perseverance rover collects first Mars rock sample
<|im_end|>
- Downloads last month
- 496
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.