0-hero/Matter-0.1-Slim-7B-preview
The 0-hero/Matter-0.1-Slim-7B-preview is a 7 billion parameter language model, a full-finetune of Mistral 7B. It was trained on the slim-D version of the Matter dataset, curated from over 35 datasets analyzing more than 6 billion tokens. This model is specifically designed with robust function calling capabilities, making it suitable for applications requiring structured interaction with external tools and APIs. It utilizes the ChatML prompt format and has a context length of 4096 tokens.
Loading preview...
Matter-0.1-Slim-7B-preview: A Function-Calling Optimized Mistral Finetune
The 0-hero/Matter-0.1-Slim-7B-preview is a 7 billion parameter model, built upon the Mistral 7B architecture through a comprehensive full-finetuning process. Its training leveraged the slim-D version of the Matter dataset, which aggregates and analyzes over 6 billion tokens from more than 35 distinct datasets.
Key Capabilities
- Advanced Function Calling: This model is specifically engineered to support function calling, incorporating dedicated tokens (
<|begin_func|>,<|end_func|>,<|begin_func_response|>,<|end_func_response|>) for seamless integration with external tools and APIs. This enables it to generate structured function calls and process their responses effectively. - ChatML Prompt Format: It adheres to the ChatML prompt format, ensuring compatibility and ease of use within chat-based applications and conversational AI systems.
- Efficient Training: The model underwent 3 epochs of full-finetuning in approximately 17 hours using Axolotl on 4x A100 GPUs (80GB).
Ideal Use Cases
- Tool-Augmented AI: Excellent for applications where the LLM needs to interact with external systems, databases, or APIs via function calls.
- Intelligent Agents: Suitable for building agents that can perform actions, retrieve real-time information, or automate tasks by invoking specific functions.
- Structured Output Generation: Its function calling capabilities make it adept at generating structured outputs that can be directly parsed and utilized by other software components.