kshabana/GOAT-llama3.1-v0.1

INTRO

we are happy to announce that we are starting our goat model family

Model Card for Model ID

this is a finetune model of llama3.1 that can perform well and we improved the general knowledge and and it can speak bunch of languages like arabic and english.

• **Developed by: kshabana
• **Funded by no one
• **Shared by kshabana
• **Model type: safetensors and gguf
• **Language(s) Arabic and English
• License: Apache2.0
• **Finetuned from model [llama3.1-instruct]

Model Sources

https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct

• Dataset Repository:

https://huggingface.co/datasets/arbml/alpaca_arabic

Uses

this model can be used for combanys that need multilagul support and it has a 131072 context lingth.

Bias, Risks, and Limitations

it can some times produce a wrong answer.

Recommendations

NOTE:you shold have lm studio or ollama to use this model

IN LM-STUDIO:it is recommended to use this model with the defult lm-studio configration. IN OLLAMA: we will be pushing the model soon to ollama.

Training Details

model trained with unsloth.

Training Data

the training dataset that i used: https://huggingface.co/datasets/arbml/alpaca_arabic

IMPORTANT LINKS

OLLAMA: https://ollama.com

LM-STUDIO: https://lmstudio.ai

llama3.1: instruct: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct

dataset: https://huggingface.co/datasets/arbml/alpaca_arabic

Results