language:
- fr
license: llama2
tags:
- pytorch
- code
inference: true
model-index:
- name: ARIA-70B-French
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 64.51
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.87
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 63.88
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 52.8
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.51
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 26.69
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
name: Open LLM Leaderboard
ARIA French is a model created from llama 2 70B finetuned on a french dataset.
contact@faradaylab.fr if you need additional support or integration to your company data.
Model Developers :FARADAY
ARIA is the first version of our models based on Llama 2-70B-Chat-HF. We finetuned llama 2 over 10.000 high quality french tokens. This version has been trained on a small dataset extract from the french parliament.
The goal is to increase model quality on French and general topics.
Aria 70B is based on Llama 2-70B-Chat-HF
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
*FINETUNING PROCESS **
We trained the model on a high quality dataset with more than 50.000 rows of french language. The training took 2 days on Amazon Cloud Sagemaker powered by Nvidia GPUs.
Timing of training
1 Day using NVIDIA A100 and a cloud service. We are grateful to Nvidia Inception program.
We are also applying rope scalling as experimental approach used by several other Open source teams to increase context lenght of ARIA from 4,096 to over 6,000 tokens. This will allow the model to handle large files for data extraction. This is not active by default and you should add a line of code at parameters to activate rope scaling.
Model Details /
Note: Use of this model is governed by the Meta license because it's based on LLAMA 2. In order to download the model weights and tokenizer, please visit the website and accept our License before requesting access here.
Variations :ARIA comes in a range of parameter sizes — 7B, 40B (based on Falcon), and 70B finetuned on French language datasets.
Input :Models input text only.
Output : Models generate text only.
Model Architecture : ARIA is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
License : A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 62.37 |
| AI2 Reasoning Challenge (25-Shot) | 64.51 |
| HellaSwag (10-Shot) | 85.87 |
| MMLU (5-Shot) | 63.88 |
| TruthfulQA (0-shot) | 52.80 |
| Winogrande (5-shot) | 80.51 |
| GSM8k (5-shot) | 26.69 |