---
license: other
license_name: nope-edge-community-license-v1.0
license_link: LICENSE.md
language:
  - en
tags:
  - safety
  - crisis-detection
  - text-classification
  - mental-health
  - content-safety
  - suicide-prevention
base_model: nopenet/nope-edge-mini
pipeline_tag: text-generation
library_name: transformers
extra_gated_heading: "Access NOPE Edge"
extra_gated_description: "This model is available for **research, academic, nonprofit, and evaluation use**. Commercial production use requires a separate license. Please read the [license terms below](#nope-edge-community-license-v10) before downloading."
extra_gated_button_content: "Agree and download"
extra_gated_fields:
  I am using this for research, academic, nonprofit, personal, or evaluation purposes:
    type: checkbox
  I agree to the NOPE Edge Community License v1.0:
    type: checkbox
---

# GGUF Files for nope-edge-mini

These are the GGUF files for [nopenet/nope-edge-mini](https://huggingface.co/nopenet/nope-edge-mini).

> [!NOTE]  
> **Note:** This is the **first iteration/revision** of this model. A revision is made when a model repo gets updated with a new model.
> 
> [[second iteration (2)](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i2)]

## Downloads

| GGUF Link | Quantization | Description |
| ---- | ----- | ----------- |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q2_K.gguf) | Q2_K | Lowest quality |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.IQ3_XS.gguf) | IQ3_XS | Integer quant |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q3_K_S.gguf) | Q3_K_S |  |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.IQ3_M.gguf) | IQ3_M | Integer quant |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q3_K_M.gguf) | Q3_K_M |  |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q3_K_L.gguf) | Q3_K_L |  |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.IQ4_XS.gguf) | IQ4_XS | Integer quant |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q5_K_S.gguf) | Q5_K_S |  |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q5_K_M.gguf) | Q5_K_M |  |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q6_K.gguf) | Q6_K | Very good quality |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.Q8_0.gguf) | Q8_0 | Best quality |
| [Download](https://huggingface.co/Flexan/nopenet-nope-edge-mini-GGUF-i1/resolve/main/nope-edge-mini.f16.gguf) | f16 | Full precision, don't bother; use a quant |

## Note from Flexan

I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet.
This process is not yet automated and I download, convert, quantize, and upload them **by hand**, usually for models **I deem interesting and wish to try out**.

If there are some quants missing that you'd like me to add, you may request one in the community tab.
If you want to request a public model to be converted, you can also request that in the community tab.
If you have questions regarding the model, please refer to the original model repo.

# NOPE Edge Mini - Crisis Classification Model

A fine-tuned model for detecting crisis signals in text - suicidal ideation, self-harm, abuse, violence, and other safety-critical content. Designed for integration into safety pipelines, content moderation systems, and mental health applications.

> **License:** [NOPE Edge Community License v1.0](LICENSE.md) - Free for research, academic, nonprofit, and evaluation use. Commercial production requires a separate license. See [nope.net/edge](https://nope.net/edge) for details.

---

## Model Variants

| Model | Parameters | Accuracy | Latency | Use Case |
|-------|------------|----------|---------|----------|
| **[nope-edge](https://huggingface.co/nopenet/nope-edge)** | 4B | **90.6%** | ~750ms | Maximum accuracy |
| **[nope-edge-mini](https://huggingface.co/nopenet/nope-edge-mini)** | 1.7B | 85.9% | ~260ms | High-volume, cost-sensitive |

This is **nope-edge-mini (1.7B)**.

---

## Quick Start

### Requirements

- Python 3.10+
- GPU with 4GB+ VRAM (e.g., RTX 3060, T4, L4) - or CPU (slower)
- ~4GB disk space

```bash
pip install torch transformers accelerate
```

### Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "nopenet/nope-edge-mini"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

def classify(message: str) -> str:
    """Returns 'type|severity|subject' or 'none'."""
    input_ids = tokenizer.apply_chat_template(
        [{"role": "user", "content": message}],
        tokenize=True,
        return_tensors="pt",
        add_generation_prompt=True
    ).to(model.device)

    with torch.no_grad():
        output = model.generate(input_ids, max_new_tokens=30, do_sample=False)

    return tokenizer.decode(
        output[0][input_ids.shape[1]:],
        skip_special_tokens=True
    ).strip()

classify("I want to end it all")                    # -> "suicide|high|self"
classify("Great day at work!")                       # -> "none"
classify("My friend said she wants to kill herself") # -> "suicide|high|other"
```

---

## Output Format

**Crisis detected:**
```
{type}|{severity}|{subject}
```

| Field | Values | Description |
|-------|--------|-------------|
| type | `suicide`, `self_harm`, `self_neglect`, `violence`, `abuse`, `sexual_violence`, `exploitation`, `stalking`, `neglect` | Risk category |
| severity | `mild`, `moderate`, `high`, `critical` | Urgency level |
| subject | `self`, `other` | Who is at risk |

**No crisis:** `none`

### Subject Attribution

| Subject | Meaning | Example |
|---------|---------|---------|
| `self` | The speaker is at risk or is the victim | "I want to kill myself", "My partner hits me" |
| `other` | The speaker is reporting concern about someone else | "My friend said she wants to die" |

### Parsing Example

```python
def parse_output(output: str) -> dict:
    output = output.strip().lower()
    if output == "none":
        return {"is_crisis": False}

    parts = output.split("|")
    return {
        "is_crisis": True,
        "type": parts[0] if len(parts) > 0 else None,
        "severity": parts[1] if len(parts) > 1 else None,
        "subject": parts[2] if len(parts) > 2 else None,
    }
```

---

## Input Best Practices

### Text Preprocessing

**Preserve natural prose.** The model was trained on real conversations with authentic expression. Emotional signals matter:

| Keep | Why |
|------|-----|
| Emojis | `💀` in "kms 💀" signals irony; `😭` signals distress intensity |
| Punctuation intensity | "I can't do this!!!" conveys more urgency than "I can't do this" |
| Casual spelling | "im so done" vs "I'm so done" — both valid, don't normalize |
| Slang/algospeak | "kms", "unalive", "catch the bus" — model understands these |

**Only remove:**

| Remove | Example |
|--------|---------|
| Zero-width/invisible Unicode | `hello\u200bworld` → `helloworld` |
| Decorative Unicode fonts | `ℐ 𝓌𝒶𝓃𝓉 𝓉𝑜 𝒹𝒾𝑒` → `I want to die` |
| Newlines (single messages) | `I can't\ndo this` → `I can't do this` |

**Keep newlines** when they provide turn structure (see Multi-Turn Conversations below).

**Examples:**

```python
# KEEP - emotional signal matters
"I can't do this anymore 😭😭😭"     # Keep emojis - signals distress
"i want to die!!!!!!!"              # Keep punctuation - signals intensity
"kms lmao 💀"                       # Keep all - irony/context signal

# NORMALIZE - only structural/invisible issues
"ℐ 𝓌𝒶𝓃𝓉 𝓉𝑜 𝒹𝒾𝑒"              → "I want to die"  # Fancy Unicode fonts
"I can't\ndo this\nanymore"        → "I can't do this anymore"  # Single message
"hello\u200bworld"                 → "helloworld"  # Zero-width chars
```

**Minimal preprocessing function:**

```python
import re
import unicodedata

def preprocess(text: str) -> str:
    # Normalize decorative Unicode fonts to ASCII (NFKC)
    text = unicodedata.normalize('NFKC', text)

    # Remove zero-width and invisible characters
    text = re.sub(r'[\u200b-\u200f\u2028-\u202f\u2060-\u206f\ufeff]', '', text)

    # Flatten newlines to spaces (for single messages only)
    text = re.sub(r'\n+', ' ', text)

    # Collapse multiple spaces
    text = re.sub(r' +', ' ', text)

    return text.strip()

# NOTE: Do NOT remove emojis, punctuation, or "normalize" spelling
```

**Language considerations:**
- Model is English-primary but handles multilingual input
- Keep native scripts (Chinese, Arabic, Korean, etc.) intact
- Preserve natural punctuation and expression in all languages

### Multi-Turn Conversations

**The model was trained on pre-serialized transcripts, not native multi-turn chat format.**

When classifying conversations, serialize into a single user message:

```python
# CORRECT - serialize conversation into single message
conversation = """User: How are you?
Assistant: I'm here to help. How are you feeling?
User: Not great. I've been thinking about ending it all."""

messages = [{"role": "user", "content": conversation}]

# WRONG - don't use multiple role/content pairs
messages = [
    {"role": "user", "content": "How are you?"},
    {"role": "assistant", "content": "I'm here to help..."},
    {"role": "user", "content": "Not great..."}
]  # Model was NOT trained this way
```

**Why serialization matters:**
- Model treats all content equally (no user/assistant distinction)
- Trained on pre-serialized transcripts for consistent attention patterns
- Native multi-turn format causes the model to "chat" instead of classify

**Flexible format - these all work:**

```python
# Simple newlines
"User: message 1\nAssistant: message 2\nUser: message 3"

# Markdown-style
"**User:** message 1\n**Assistant:** message 2"

# Labeled
"{user}: message 1\n{assistant}: message 2"

# XML-style
"<user>message 1</user>\n<assistant>message 2</assistant>"
```

The model is robust to formatting variations. Consistency matters more than specific format choice.

### Input Length

- **Single messages:** No preprocessing needed beyond character cleanup
- **Conversations:** For very long conversations (20+ turns), consider:
  - Classifying a sliding window (last 10-15 turns)
  - The model's attention may not span extremely long contexts effectively
  - Deep needle detection (crisis buried in turn 3 of 25) is a known limitation

---

## Production Deployment

For high-throughput production use, deploy with vLLM or SGLang:

```bash
# vLLM
pip install vllm
python -m vllm.entrypoints.openai.api_server \
    --model nopenet/nope-edge-mini \
    --dtype bfloat16 --max-model-len 2048 --port 8000

# SGLang
pip install sglang
python -m sglang.launch_server \
    --model nopenet/nope-edge-mini \
    --dtype bfloat16 --port 8000
```

Then call as OpenAI-compatible API:

```bash
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nopenet/nope-edge-mini",
    "messages": [{"role": "user", "content": "I want to end it all"}],
    "max_tokens": 30, "temperature": 0
  }'
```

| Setup | Throughput | Latency (p50) |
|-------|-----------|---------------|
| transformers | ~8 req/sec | ~180ms |
| vLLM / SGLang | 50-100+ req/sec | ~50ms |

---

## Model Details

| | |
|---|---|
| **Parameters** | 1.7B |
| **Precision** | bfloat16 |
| **Base Model** | Qwen/Qwen3-1.7B |
| **Method** | LoRA fine-tune, merged to full weights |
| **License** | [NOPE Edge Community License v1.0](LICENSE.md) |

---

## Risk Types Detected

| Type | Description | Clinical Framework |
|------|-------------|-------------------|
| `suicide` | Suicidal ideation, intent, planning | C-SSRS |
| `self_harm` | Non-suicidal self-injury (NSSI) | - |
| `self_neglect` | Eating disorders, medical neglect | - |
| `violence` | Threats/intent to harm others | HCR-20 |
| `abuse` | Domestic/intimate partner violence | DASH |
| `sexual_violence` | Rape, sexual assault, coercion | - |
| `neglect` | Failing to care for dependent | - |
| `exploitation` | Trafficking, grooming, sextortion | - |
| `stalking` | Persistent unwanted contact | SAM |

---

## Important Limitations

- Outputs are **probabilistic signals**, not clinical assessments
- **False negatives and false positives will occur**
- Never use as the **sole basis** for intervention decisions
- Always implement **human review** for flagged content
- This model is **not** a medical device or substitute for professional judgment
- Not validated for all populations, languages, or cultural contexts

---

## Commercial Licensing

This model is free for research, academic, nonprofit, and evaluation use.

**For commercial production deployment**, contact us:
- Email: support@nope.net
- Website: https://nope.net/edge

Commercial licenses include:
- Production deployment rights
- Priority support
- Custom fine-tuning options
- SLA guarantees

---

## About NOPE

NOPE provides safety infrastructure for AI applications. Our API helps developers detect mental health crises and harmful AI behavior in real-time.

- **Website:** https://nope.net
- **Documentation:** https://docs.nope.net
- **Support:** support@nope.net

---

## NOPE Edge Community License v1.0

Copyright (c) 2026 NopeNet, LLC. All rights reserved.

### Permitted Uses

You may use this Model for:

- **Research and academic purposes** - published or unpublished studies
- **Personal projects** - non-commercial individual use
- **Nonprofit organizations** - including crisis lines, mental health organizations, and safety-focused NGOs
- **Evaluation and development** - testing integration before commercial licensing
- **Benchmarking** - publishing evaluations with attribution

### Commercial Use

**Commercial use requires a separate license.** Commercial use includes production deployment in revenue-generating products or use by for-profit companies beyond evaluation.

Contact support@nope.net or visit https://nope.net/edge for commercial licensing.

### Restrictions

You may NOT: redistribute or share weights; sublicense, sell, or transfer the Model; create derivative models for redistribution; build a competing crisis classification product.

### No Warranty

THE MODEL IS PROVIDED "AS IS" WITHOUT WARRANTIES. False negatives and false positives will occur. This is not a medical device or substitute for professional judgment.

### Limitation of Liability

NopeNet shall not be liable for damages arising from use, including classification errors or harm to any person.

### Base Model

Built on [Qwen3](https://huggingface.co/Qwen) by Alibaba Cloud (Apache 2.0). See NOTICE.md.