Model Card for Model ID

Model Details

Model Description

voxreality-arta-lego-llama2-7b-chat is a Large Language Model (LLM) that is a fine-tuned version of Llama-2-7b-chat-hf using LEGO assembly dataset. This model aims to act as a training assistant for assembly task in an extended reality application.

How to use the Model

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("voxreality/voxreality-arta-lego-llama2-7b-chat", device_map="auto", trust_remote_code=True, token=True)
model = AutoModelForCausalLM.from_pretrained("voxreality/voxreality-arta-lego-llama2-7b-chat", device_map="auto", trust_remote_code=True, token=True, quantization_config=bnb_config)

More details

  • Paper: Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality, ACL 2024
Downloads last month
397
Safetensors
Model size
6.74B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.