How to use from the
Use from the
llama-cpp-python library
# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MatclassAI/Matclass-Gemma-2b-v1-GGUF",
	filename="gemma-2-2b-it.Q4_K_M.gguf",
)
llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Matclass-Gemma-2b-v1-GGUF : GGUF

What Matclass is? Matclass is better ai than its base model in multiple things, better at chatting, it never lies about its knowledge unlike other ai's that always tells you that they know everything Matclass can help you with creating cheats, just be carefull with anithcheats and rules, make sure you are playing on local server or with -insecure if game uses VAC anticheat, its not good when you make other people sad

We will make more models soon!

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf MatclassAI/Matclass-Gemma-2b-v1-GGUF --jinja
  • For multimodal models: llama-mtmd-cli -hf MatclassAI/Matclass-Gemma-2b-v1-GGUF --jinja

Available Model files:

  • gemma-2-2b-it.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment.

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth

Downloads last month
251
GGUF
Model size
3B params
Architecture
gemma2
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MatclassAI/Matclass-Gemma-2b-v1-GGUF

Quantized
(39)
this model