MalayaLLM_Gemma_2_2B_Instruct_V1.0_GGUF

MalayaLLM: Gemma-2-2B [മലയാളം/Malayalam]

<img src="https://github.com/VishnuPJ/MalayaLLM-Gemma2-9B/assets/54801493/19ea32ea-04ba-4198-aab3-cbcdd0c3bc7b" alt="Baby MalayaLLM" width="300" height="auto">

Introducing the Developer:

Discover the mind behind this model and stay updated on their contributions to the field https://www.linkedin.com/in/vishnu-prasad-j/

Model description

The MalayaLLM models have been improved and customized expanding upon the groundwork laid by the original Gemma-2-2B model.

• Model type: A 2B Gemma-2 finetuned model on Malayalam tokens.
• Language(s): Malayalam and English
• Datasets:
  • CohereForAI/aya_dataset
  • wikimedia/wikipedia
• Source Model: MalayaLLM_Gemma_2_2B_Base_V1.0
• Instruct Model: MalayaLLM_Gemma_2_2B_Instruct_V1.0
• GGUF Model: MalayaLLM_Gemma_2_2B_Instruct_V1.0_GGUF
• Training Precision: float16

Old Model

Gemma-7B,9B trained model is here :MalayaLLM:Gemma-7B

How to run GGUF

• llama.cpp Web Server

  • The web server is a lightweight HTTP server that can be used to serve local models and easily connect them to existing clients.

• Building llama.cpp

  • To build llama.cpp locally, follow the instructions provided in the build documentation.

• Running llama.cpp as a Web Server

  • Once you have built llama.cpp, you can run it as a web server. Below is an example of how to start the server:

    llama-server.exe -m gemma_2_9b_instruction.Q4_K_M.gguf -ngl 42 -c 128 -n 100
    

• Accessing the Web UI

  • After starting the server, you can access the basic web UI via your browser at the following address: http://localhost:8080 <img src="https://cdn-uploads.huggingface.co/production/uploads/64e65800e44b2668a56f9731/te7d5xjMrtk6RDMEAxmCy.png" alt="Baby MalayaLLM" width="600" height="auto">

Made Using UNSLOTH

Thanks to Unsloth, the process of fine-tuning large language models (LLMs) has become much easier and more efficient.

<img src="https://cdn-uploads.huggingface.co/production/uploads/64e65800e44b2668a56f9731/WPt_FKUWDdc6--l_Qnb-G.png" alt="Unsloth" width="200" height="auto">

🌟Happy coding💻🌟