Instructions to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Use Docker

docker model run hf.co/jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Llama new
LM Studio
Jan
Ollama
How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with Ollama:
```
ollama run hf.co/jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16
```
Unsloth Desktop

How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16
```

Lemonade

How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3-1.7B-teacher-note-severity-v2-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3-1.7B Teacher Note Severity v2 — GGUF

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

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.
Load the model; 2k–8k context works for single notes; raise it (up to 32k) for long running logs.
Set the system prompt (below). Keep thinking mode off so the answer is pure JSON.
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.