simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4
Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4: Optimized for SiMa.ai Modalix
Overview
This repository contains the Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4 model, optimized and compiled for the SiMa.ai Modalix platform.
- Model Architecture: Llama 3.1 Swallow (8B parameters)
- Languages: Japanese and English
- Quantization: A16W4 (BF16 activations, INT4 weights)
- Pre-quantization: The source checkpoint was pre-quantized with GPTQ before compilation.
- Maximum context length: 8192
- Source Model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
- Quantized Checkpoint: simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-Safetensors
Llama 3.1 Swallow extends Meta Llama 3.1 with enhanced Japanese-language capabilities while retaining English-language capabilities. This repository contains SiMa.ai compiled deployment artifacts and is not a Transformers checkpoint.
Performance
The following measurements characterize text generation on Modalix.
Measured with MoLE using batch size 1, five samples per input length, and up to 128 generated tokens. Values are arithmetic means. TTFT includes language-model prefill and the first generated token; generation rate is measured after the first token.
Prerequisites
To run this model, you need:
- SiMa.ai Modalix Device
- SiMa.ai CLI: Installed on your Modalix device.
- SiMa.ai Neat Runtime: Install or update the Neat Library on Modalix. The LLiMa runtime is installed as part of the Neat runtime.
- Hugging Face CLI: Optional, for downloading the model on a host before copying it to Modalix.
Installation & Deployment
Follow these steps to deploy the model to your Modalix device.
1. Install or Update Neat Runtime
Note: This is a one-time setup. If the Neat Library is already installed on your Modalix device, you can skip this step and continue with model download.
Follow the SiMa.ai Neat getting started guide to install or update the Neat Library on your Modalix device.
The llima CLI is available on Modalix after the Neat runtime is installed. It manages precompiled GenAI models under /media/nvme/llima/models by default. Set LLIMA_MODELS_PATH to use a different model directory.
2. Download the Model
Download the compiled model assets from this repository directly to your device.
llima pull Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4Alternatively, download the compiled model to a host and copy it to the Modalix device:
hf download simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4 \
--local-dir Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4
scp -r Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4 \
sima@<modalix-ip>:/media/nvme/llima/models/Replace <modalix-ip> with the IP address of your Modalix device.
Expected Directory Structure:
/media/nvme/llima/
└── models/
└── Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4/ # The compiled modelUsage
Validate with LLiMa CLI
Run the model directly on Modalix:
llima run Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-a16w4For all runtime options, run:
llima run -hGenAI Demo Application
The GenAI demo application is separate from LLiMa installation. Use the GenAI Multimodal Assistant page to install and run the demo app. Once installed, the demo app can use precompiled models such as this one.
API Usage
To serve this model with OpenAI- or Ollama-compatible APIs and send requests to it, use the GenAI server workflow in Serve GenAI Models.
For direct LLM calls without setting up a server, see Run an LLM.
Limitations
- Quantization: This model is quantized to A16W4 for efficient execution on embedded devices. Outputs may differ from the source model due to quantization.
- Platform: The compiled artifacts in this repository are intended for SiMa.ai Modalix and cannot be loaded directly with Hugging Face Transformers.
- Language and task coverage: Validate quality with representative Japanese and English prompts from the intended deployment workload.
- License and acceptable use: Use is subject to the source model's Llama 3.3 and Gemma license terms, intended-use guidance, and restrictions. Review the source model card and included license materials before use or redistribution.
Troubleshooting
- `sima-cli` not found: Ensure that
sima-cliis installed on your Modalix device. - `llima` not found: Install or update the Neat Library. See Getting Started.
- Model can't be run: Verify that the model directory is directly inside
/media/nvme/llima/models/and not nested inside another directory with the same name. - Permission denied: Ensure that you have read/write permissions for
/media/nvme.
