---
license: mit
---
# MalayaLLM: Gemma-2 [മലയാളം/Malayalam]
# 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 model.
- **Model type:** A 9B Gemma-2 finetuned model on Malayalam tokens.
- **Language(s):** Malayalam and English
- **Datasets:** [CohereForAI/aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset)
- **Source Model:** [MalayaLLM_Gemma_2_9B_Base_V1.0](https://huggingface.co/VishnuPJ/MalayaLLM_Gemma_2_9B_Base_V1.0)
- **Instruct Model:** [MalayaLLM_Gemma_2_9B_Instruct_V1.0](https://huggingface.co/VishnuPJ/MalayaLLM_Gemma_2_9B_Instruct_V1.0)
- **Training Precision:** `float16`
- **Github Repo:** [MalayaLLM-Gemma2-9B](https://github.com/VishnuPJ/MalayaLLM-Gemma2-9B)
# Old Model
Gemma trained model is here :[MalayaLLM: Gemma-7B](https://huggingface.co/collections/VishnuPJ/malayallm-malayalam-gemma-7b-66851df5e809bed18c2abd25)
## 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](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md).
- #### 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:
```sh
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](http://localhost:8080)
## Made Using UNSLOTH
Thanks to [Unsloth](https://github.com/unslothai/unsloth), the process of fine-tuning large language models (LLMs) has become much easier and more efficient.
# 🌟Happy coding💻🌟