Arabic-Orpo-Llama-3-8B-InstructMohamedRashad
Start Chat
8B Params FP8 Inference Available

MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct is an 8 billion parameter instruction-tuned causal language model fine-tuned by MohamedRashad from Meta-Llama-3-8B-Instruct using the ORPO method. This model is specifically optimized for generating coherent Arabic text, despite formal evaluations showing a slight decrease in Arabic MMLU scores compared to its base model. It aims to better align the Llama 3 architecture for Arabic language tasks, offering a practical improvement in Arabic text generation.

Loading preview...

Parameters:8BContext length:8kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:April 2024
0.0M
0.0K

Model tree for

MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

0.3

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

1

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

–

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

–

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

–

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

–

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.

–