SAVRN
Search Contact SAVRN

Open-weight model

Qwen3-1.7B-teacher-note-severity-v2-GGUF

by Jeremie Rostan jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF

Qwen3-1.7B-teacher-note-severity-v2-GGUF is an open-weight model from Jeremie Rostan, released under Apache License 2.0. Its published files total 5.3 GB.

GGUF builds of jeremierostan/Qwen3-1.7B-teacher-note-severity-v2, which adds an inclass / outsideclass location field to the v1 severity model - Qwen3-1.7B-teacher-note-severity-v2-f16.gguf (3.4 GB) — full precision …

Parameters
Context
Weights5.3 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads

Model Card

By Jeremie Rostan, published under apache-2.0, revision ff255c48b425.

GGUF builds of jeremierostan/Qwen3-1.7B-teacher-note-severity-v2, which adds an inclass / outsideclass location field to the v1 severity model - Qwen3-1.7B-teacher-note-severity-v2-f16.gguf (3.4 GB) — full precision - Qwen3-1.7B-teacher-note-severity-v2-q80.gguf (1.8 GB) — recommended; near-identical quality, half the size Given a teacher note (or a running log of notes), the model replies with a single JSON object: Commendations score negative; routine notes 5–55; severity >= 60 means escalate to admin (escalate is set exactly when severity >= 60, across all categories). 1. In LM Studio, search this repo id (jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF) and download the q80 file…

Read Jeremie Rostan's full model card

GGUF builds of jeremierostan/Qwen3-1.7B-teacher-note-severity-v2, which adds an in_class / outside_class location field to the v1 severity model (v1 GGUF here).

Files:

  • Qwen3-1.7B-teacher-note-severity-v2-f16.gguf (3.4 GB) — full precision
  • Qwen3-1.7B-teacher-note-severity-v2-q8_0.gguf (1.8 GB) — recommended; near-identical quality, half the size

Output format

Given a teacher note (or a running log of notes), the model replies with a single JSON object:

{"category": "commendation | misbehavior | academic_concern", "location": "in_class | outside_class", "severity": <int -100..100>, "escalate": <bool>}

Commendations score negative; routine notes 5–55; severity >= 60 means escalate to admin (escalate is set exactly when severity >= 60, across all categories).

LM Studio

  1. In LM Studio, search this repo id (jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF) and download the q8_0 file, or place the file in your models folder.
  2. Load the model; 2k–8k context works for single notes; raise it (up to 32k) for long running logs.
  3. Set the system prompt (below). Keep thinking mode off so the answer is pure JSON.
  4. Paste a note. Expected reply: JSON only.

System prompt

You are a school record assistant. Classify the teacher note about a student. Respond with ONLY a JSON object with keys: "category" (one of "commendation", "misbehavior", "academic_concern"), "location" ("in_class" for behavior during class or class activities, "outside_class" for behavior in hallways, cafeteria, playground, bus, online or other non-classroom settings), "severity" (integer, -100 to 100: commendations are negative, routine notes are 5-55, serious concerns warranting admin attention are 60 or above), and "escalate" (true only if severity >= 60).

Eval (held-out synthetic test, n=200)

  • Band accuracy 0.930 · Category accuracy 0.990 · Location accuracy 0.990
  • Severity MAE 12.83 · Escalate F1 1.000 · JSON parsable 1.000

Notes

  • Trained on synthetic data (jeremierostan/teacher-notes-severity-v2); validate on real notes before production use.
  • Severity within a band is approximate; treat it as triage, not a grade.

Identity and Version

Repository
jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF
Publisher
Jeremie Rostan
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
ff255c48b425bc3d1e0ec6f9f64d8eeb9d47d52d
First published
2026-09-20
Last updated
2026-09-20

Files and Weights

4 files, 5.3 GB in total. The weights are 2 files totalling 5.3 GB in gguf.

Weights2 files · 5.3 GB
Documentation1 file · 2.5 KB
Repository1 file · 1.7 KB
Every file
FileTypeSizeSHA-256
Qwen3-1.7B-teacher-note-severity-v2-f16.ggufWeights3.4 GB b88037dcaf19
Qwen3-1.7B-teacher-note-severity-v2-q8_0.ggufWeights1.8 GB 79be5a7ecbc8
README.mdDocumentation2.5 KB
.gitattributesRepository1.7 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
5.3 GB
Download from Jeremie Rostan

Released by Jeremie Rostan through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published5.3 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Qwen3-1.7B-teacher-note-severity-v2-GGUF

Can I use Qwen3-1.7B-teacher-note-severity-v2-GGUF commercially?

Yes. Qwen3-1.7B-teacher-note-severity-v2-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.