EnnoAi-Pro-Llama-3-8B

French Pro model

This version aims to be a multilingual model (EN 🇺🇸 + FR 🇫🇷) to refine the specific professional tasks in French.

Dataset

EnnoAi-Pro has been trained on a French dataset to enhance its analysis and response quality. The dataset contains ~275K high-quality training samples of professional and general strategic themes.

Tuning

We use specific recipes with QLora methods to increase accuracy in advanced RAG contexts.

Prompt Format

We use the default ChatML format with system role support.

<|begin_of_text|><|im_start|>system
{SYSTEM_CONTEXT}<|im_end|>
<|im_start|>user
{USER_ENTRY}<|im_end|>
<|im_start|>assistant
{ASSISTANT_ENTRY}<|im_end|>

This model is under construction

Open LLM Leaderboard Evaluation Results

Detailed results can be found here