Edit model card

Matter 7B - 0.2 - GGUF (Mistral 7B 0.2 Finetune)

This is the GGUF version of the model, made for the llama.cpp inference engine.

Model Description

Matter 7B 0.2 is full-finetune on the Matter 0.2 dataset (not yet released), which is curated from over 35 datsets analyzing >6B tokens

Training

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

  • <tool_call> - Function call start token
  • </tool_call> - Function call end token

Function call response tokens

  • <tool_response> - Function response start token
  • </tool_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
  <tool_call>{"name": "get_news_headlines", "arguments": '{"country": "United States"}'}</tool_call><|im_end|>
<|im_start|>user
  <tool_response>{
    "headlines":
      [
        "Biden announces new vaccine mandates",
        "Hurricane Ida devastates Louisiana",
        "Apple unveils new iPhone",
        "NASA's Perseverance rover collects first Mars rock sample"
      ]
  }</tool_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
133
GGUF
Model size
7.24B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for QuantFactory/Matter-0.2-7B-GGUF

Quantized
(1)
this model