Downloads · 30 days
2
1% of all-time downloads
zyoralabs/AQ-academic-ai-GGUF
AQ-academic-ai-GGUF is a text generation model from zyoralabs. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This repository contains an experimental English-only edge preview of zyoralabs/AQ-academic-ai, a 1.26B-parameter academic tutor built from scratch by Zyora Labs.
Downloads · 30 days
2
1% of all-time downloads
All-time downloads
135
Public
Repo size
765 MB
Likes
0
Public
Click a slice to open those files.
.gguf765 MB · 100%
From the Hugging Face model README
This repository contains an experimental English-only edge preview of zyoralabs/AQ-academic-ai, a 1.26B-parameter academic tutor built from scratch by Zyora Labs.
| File | Quantization | Size | Context |
|---|---|---|---|
aq-tutor-v2-q4_k_m.gguf | Q4_K_M | 765,358,592 bytes (~730 MiB) | 2,048 tokens |
SHA-256:
b675e036ace4934835bf323ee43fc39dca0d2fbb5d3c0435e3c680c2ea4aa278
llama-cli \
-m aq-tutor-v2-q4_k_m.gguf \
-p $'### Student:\nWhat is photosynthesis?\n\n### Tutor:\n' \
-n 200 --temp 0.7 --top-k 40 --repeat-penalty 1.3 --ctx-size 2048
2x; photosynthesis → coherent academic explanation.19482cacfa3a1157fce7a51a22285ec10f689133.153d324bcf86d220b235ca010eeb11213f32b5d1.This Q4 artifact is currently released as an English-only preview. Tamil and Hindi generation did not pass release-quality checks. Do not represent this GGUF as a validated multilingual release. The authoritative BF16 model remains in the source repository.
Quantization creates approximate derivative weights; it does not alter the original AQ weights.