Downloads · 30 days
9
3% of all-time downloads
diegobit/llama-3-8b-ita-4k-orpo-v3
llama-3-8b-ita-4k-orpo-v3 is a text generation model from diegobit. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
This is llama-3-8b ORPO finetuning for the italian language over a concatenation of two datasets: - mii-community/ultrafeedback-preferences-translated-ita - efederici/alpaca-vs-alpaca-orpo-dpo
Downloads · 30 days
9
3% of all-time downloads
All-time downloads
345
Public
Parameters
8.2B
5.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.7 GB · 100%
How the weights are stored.
U87.2B · 87%
From the Hugging Face model README
This is llama-3-8b ORPO finetuning for the italian language over a concatenation of two datasets:
The other two differences with diegobit/llama-3-8b-Instruct-bnb-4bit-ita-orpo are:
astronomer/Llama-3-8B-Special-Tokens-Adjusted instead of unsloth/llama-3-8b-Instruct-bnb-4bitunsloth: 2024.5
torch: 2.2
mii-community/ultrafeedback-preferences-translated-ita is a selection of 55k rows of the ultrafeedback dataset, translated into italian with argotranslate.efederici/alpaca-vs-alpaca-orpo-dpo: The Alpaca vs. Alpaca dataset is a curated blend of the Alpaca dataset and the Alpaca GPT-4 dataset, both available on HuggingFace Datasets. It uses the standard GPT dataset as the 'rejected' answer, steering the model towards the GPT-4 answer, which is considered as the 'chosen' one.No preprocessing has been performed, except for formatting with the llama3 chat_template from unsloth:
tokenizer = get_chat_template(tokenizer, chat_template = "llama-3")
Training regime: bf16
Model loading parameters:
max_seq_length = 4096
dtype = None
load_in_4bit = False
r = 64
lora_alpha = 64
lora_dropout = 0
bias = "none"
random_state = 3407
use_rslora = False
loftq_config = None
max_length = 4096
max_prompt_length = max_seq_length//2
max_completion_length = max_seq_length//2
warmup_ratio = 0.1
weight_decay = 0.01
per_device_train_batch_size = 1
gradient_accumulation_steps = 16
learning_rate=8e-6
beta = 0.1
optim = "paged_adamw_8bit"
lr_scheduler_type = "linear"
num_train_epochs = 1
19h on an A100-40GB