What are the hardware requirements for IndusQ?

IndusQ requires approximately 2.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed IndusQ and how large is it?

IndusQ is developed by nbrahme, a model with 1.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate IndusQ?

IndusQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

IndusQ by nbrahme — VRAM 2.4GB

Name: IndusQ
Author: nbrahme

IndusQ is an open-source language model by nbrahme. Features: 1.1b LLM, VRAM: 2.4GB, License: osl-3.0, LLM Explorer Score: 0.16.

Gpt2 Model-index Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nbrahme/IndusQ

IndusQ Parameters and Internals

LLM Name	IndusQ
Repository 🤗	https://huggingface.co/nbrahme/IndusQ
Model Size	1.1b
Required VRAM	2.4 GB
Updated	2024-09-27
Maintainer	nbrahme
Model Type	gpt2
Model Files	2.4 GB
Model Architecture	GPT2LMHeadModel
License	osl-3.0
Model Max Length	1024
Transformers Version	4.44.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	</s>
Vocabulary Size	32300
Torch Data Type	bfloat16
Activation Function	gelu_new

Rank the IndusQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to IndusQ

Best Alternatives	Context / RAM	Downloads	Likes
Floppyx3 MEGAmodel Merged	0K / 0 GB	1421	0
Floppyx3 MEGAmodel Base	0K / 0 GB	37	0
ProjectIndus	0K / 2.4 GB	132	22

Note: green Score (e.g. "73.2") means that the model is better than nbrahme/IndusQ.