Model Overview
- Model Architecture: Exaone
- Input: Text
- Output: Text
- Model Optimizations:
- Context Length: 32k tokens
- Maximum Prompt Length: 32768 tokens
- Maximum Generation Length: 32768 tokens
- Intended Use Cases: Intended for commercial and non-commercial use. Same as EXAONE-3.5-7.8B-Instruct, this models is intended for assistant-like chat.
- Release Date: 04/12/2025
- Version: v2025.2
- License(s): EXAONE AI Model License Agreement 1.1
- Supported Inference Engine(s): Furiosa LLM
- Supported Hardware Compatibility: FuriosaAI RNGD
- Preferred Operating System(s): Linux
- Quantization: No
- Datasets:
Description:
The FuriosaAI EXAONE-3.5-7.8B-Instruct is the pre-compiled version of the EXAONE-3.5-7.8B-Instruct, which is an auto-regressive language model that uses an optimized transformer architecture.
This model is ready for commercial and non-commercial use.
Usage
To run this model with Furiosa-LLM, follow the sample command below after installing Furiosa-LLM and its prerequisites.
furiosa-llm serve furiosa-ai/EXAONE-3.5-7.8B-Instruct
- Downloads last month
- 5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The HF Inference API does not support text-generation models for furiosa-llm
library.
Model tree for furiosa-ai/EXAONE-3.5-7.8B-Instruct
Base model
LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct