457 lines
13 KiB
Markdown
457 lines
13 KiB
Markdown
---
|
||
language:
|
||
- en
|
||
license: apache-2.0
|
||
pipeline_tag: text-generation
|
||
library_name: transformers
|
||
tags:
|
||
- llm
|
||
- instruction-tuned
|
||
- text-generation
|
||
- conversational
|
||
- open-world
|
||
- web-search
|
||
- anti-tic
|
||
- warm-personality
|
||
- lora
|
||
- lightweight
|
||
- safetensors
|
||
- causal-lm
|
||
- phi3
|
||
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
||
fine_tuned_from: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
||
organization: QuantaSparkLabs
|
||
model_type: causal-lm
|
||
model-index:
|
||
- name: Antiplex-Instruct-3B
|
||
results:
|
||
- task:
|
||
type: text-generation
|
||
name: Conversational Quality
|
||
dataset:
|
||
name: antiplex-eval-set
|
||
type: Custom
|
||
metrics:
|
||
- name: Anti‑Tic Success Rate
|
||
type: accuracy
|
||
value: 1.0
|
||
verified: false
|
||
- name: Factual Accuracy
|
||
type: accuracy
|
||
value: 0.85
|
||
verified: false
|
||
- name: Coherence Score
|
||
type: accuracy
|
||
value: 0.88
|
||
verified: false
|
||
- name: Conversational Warmth
|
||
type: accuracy
|
||
value: 0.90
|
||
verified: false
|
||
- task:
|
||
type: text-generation
|
||
name: Grammar & Spelling
|
||
dataset:
|
||
name: antiplex-eval-set
|
||
type: Custom
|
||
metrics:
|
||
- name: Grammar Accuracy
|
||
type: accuracy
|
||
value: 0.92
|
||
verified: false
|
||
- task:
|
||
type: text-generation
|
||
name: Real‑World Test Suite
|
||
dataset:
|
||
name: QuantaSparkLabs/antiplex-test-suite
|
||
type: Custom
|
||
metrics:
|
||
- name: Anti‑Tic Success Rate
|
||
type: accuracy
|
||
value: 1.0
|
||
verified: false
|
||
note: "Manual evaluation on antiplex-test-suite"
|
||
- name: Factual Accuracy
|
||
type: accuracy
|
||
value: 0.85
|
||
verified: false
|
||
note: "Manual evaluation on antiplex-test-suite"
|
||
- name: Coherence Score
|
||
type: accuracy
|
||
value: 0.88
|
||
verified: false
|
||
note: "Manual evaluation on antiplex-test-suite"
|
||
- task:
|
||
type: text-generation
|
||
name: Open LLM Leaderboard
|
||
dataset:
|
||
name: open-llm-leaderboard
|
||
type: benchmark
|
||
metrics:
|
||
- name: MMLU (5-shot)
|
||
type: accuracy
|
||
value: 0.0
|
||
verified: false
|
||
note: "Pending — submit to Open LLM Leaderboard"
|
||
- name: HellaSwag (10-shot)
|
||
type: accuracy
|
||
value: 0.0
|
||
verified: false
|
||
note: "Pending — submit to Open LLM Leaderboard"
|
||
- name: TruthfulQA (0-shot)
|
||
type: accuracy
|
||
value: 0.0
|
||
verified: false
|
||
note: "Pending — submit to Open LLM Leaderboard"
|
||
- name: ARC (25-shot)
|
||
type: accuracy
|
||
value: 0.0
|
||
verified: false
|
||
note: "Pending — submit to Open LLM Leaderboard"
|
||
---
|
||
<p align="center">
|
||
<img src="https://huggingface.co/QuantaSparkLabs/NYXIS-Pro/resolve/main/preview imgagee.png"
|
||
alt="NYXIS Logo"
|
||
width="160"
|
||
height="160"
|
||
style="border-radius: 50%; object-fit: cover;">
|
||
</p>
|
||
|
||
<p align="center">
|
||
<img src="https://huggingface.co/QuantaSparkLabs/NYXIS-Pro/resolve/main/logoname.png"
|
||
alt="NYXIS Name"
|
||
width="700"
|
||
style="border-radius: 18px;">
|
||
</p>
|
||
|
||
<h1 align="center">Antiplex-Instruct-3B</h1>
|
||
|
||
<p align="center">
|
||
A warm, direct, open‑world conversational AI built on <strong>Phi‑3‑mini</strong> — no corporate bot vibes, just honest chat.
|
||
</p>
|
||
|
||
<p align="center">
|
||
<a href="https://huggingface.co/microsoft/Phi-3-mini-4k-instruct"><img src="https://img.shields.io/badge/Base-Phi--3--mini--4k-blueviolet" alt="Base Model"></a>
|
||
<a href="https://huggingface.co/datasets/teknium/OpenHermes-2.5"><img src="https://img.shields.io/badge/Data-OpenHermes%202.5-00BFFF" alt="Training Data"></a>
|
||
<a href="#"><img src="https://img.shields.io/badge/Fine--Tune-QLoRA%20%2B%20Unsloth-FF6F00" alt="Fine-Tune Method"></a>
|
||
<a href="#"><img src="https://img.shields.io/badge/Anti--Tic-No%20%22How%20may%20I%22-brightgreen" alt="Anti-Tic Identity"></a>
|
||
<a href="#"><img src="https://img.shields.io/badge/Web%20Search-Tool--Ready-lightgrey" alt="Web Search"></a>
|
||
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-yellow" alt="License"></a>
|
||
</p>
|
||
|
||
<div style="background: #dc3545; color: #ffffff; padding: 15px 20px; border-radius: 8px; margin: 20px 0;">
|
||
|
||
### ⚠️ Important
|
||
|
||
This model has been **completely rebuilt** from the ground up. The previous version suffered from corrupted config files, fused-weight mismatches, and gibberish output. Those issues are now fully resolved.
|
||
**You can load the model directly with `AutoModelForCausalLM.from_pretrained`** — no special libraries, no hacks, no "as an AI" deflections.
|
||
Please review the model files (`config.json`, `model.safetensors`, and tokenizer files) before installation to ensure you are using the latest version.
|
||
MODEL work done.
|
||
|
||
</div>
|
||
|
||
---
|
||
|
||
## 📋 Overview
|
||
|
||
**Antiplex-Instruct-3B** is a high-performance instruction-tuned language model developed by **QuantaSparkLabs**. Released in 2026, this model is engineered for dual-task capability, delivering accurate identity alignment, reliable SQL generation, and strong general reasoning, while remaining lightweight and efficient.
|
||
|
||
The model is fine-tuned using **LoRA (PEFT)** on curated datasets emphasizing identity consistency and structured reasoning, making it ideal for edge deployment and specialized assistant roles.
|
||
|
||
## ✨ Core Features
|
||
|
||
| 🎯 Task Versatility | ⚡ Performance Optimized |
|
||
| :--- | :--- |
|
||
| **Text Generation**: SQL/NLP, creative writing, technical explanations. | **LoRA Fine-tuning**: Efficient parameter adaptation. |
|
||
| **Classification**: Intent detection, task routing, safety filtering. | **Identity Alignment**: Consistent persona across interactions. |
|
||
| **Dual-Mode**: Single model handling generation + classification. | **Lightweight**: ~3.8B parameters, edge-friendly VRAM footprint. |
|
||
<p align="center">
|
||
<img src="statics.png" width="900" alt="statics"/>
|
||
</p>
|
||
---
|
||
|
||
## 📊 Performance Benchmarks
|
||
|
||
### 🏆 Accuracy Metrics
|
||
| Task | Accuracy | Confidence |
|
||
| :--- | :--- | :--- |
|
||
| Identity Verification | 100% | ⭐⭐⭐⭐⭐ |
|
||
| SQL Generation | 100% | ⭐⭐⭐⭐⭐ |
|
||
| General Reasoning | 90% | ⭐⭐⭐⭐ |
|
||
|
||
### 🔬 Reliability Assessment
|
||
**21-Test Internal Validation Suite**
|
||
* **Passed:** 16 tests (76.2%)
|
||
* **Failed:** 5 tests (23.8%)
|
||
* **Overall Grade:** B (Good)
|
||
<p align="center">
|
||
<img src="overview.png" width="900" alt="overview"/>
|
||
</p>
|
||
|
||
<details>
|
||
<summary>📈 View Detailed Test Categories</summary>
|
||
|
||
| Category | Tests | Passed | Rate |
|
||
| :--- | :--- | :--- | :--- |
|
||
| Identity Tasks | 7 | 7 | 100% |
|
||
| SQL Generation | 6 | 6 | 100% |
|
||
| Reasoning | 5 | 3 | 60% |
|
||
| Classification | 3 | 2 | 66.7% |
|
||
|
||
**Test Dataset:** `QuantaSparkLabs/antiplex-test-suite`
|
||
</details>
|
||
|
||
---
|
||
|
||
## 🏗️ Model Architecture
|
||
|
||
### Training Pipeline
|
||
```mermaid
|
||
graph TD
|
||
A[Base Model Phi-3-mini] --> B[LoRA Fine-tuning]
|
||
B --> C[Task-Specific Heads]
|
||
C --> D[Text Generation Head]
|
||
C --> E[Classification Head]
|
||
D --> F[Generation Output]
|
||
E --> G[Classification Output]
|
||
H[Instruction Dataset] --> B
|
||
I[SQL Dataset] --> B
|
||
J[Identity Dataset] --> B
|
||
```
|
||
<p align="center">
|
||
<img src="structure.png" width="900" alt="structure"/>
|
||
</p>
|
||
|
||
### Inference Flow
|
||
```
|
||
User Prompt → Tokenization → Antiplex Core → Task Router
|
||
↓
|
||
[Generation/Classification] → Post-processing → Output
|
||
```
|
||
|
||
---
|
||
|
||
## 🔧 Technical Specifications
|
||
|
||
| Parameter | Value |
|
||
| :--- | :--- |
|
||
| **Base Model** | `unsloth/Phi-3-mini-4k-instruct-bnb-4bit` |
|
||
| **Fine-tuning** | LoRA (PEFT) |
|
||
| **Rank (r)** | 16 |
|
||
| **Alpha (α)** | 32 |
|
||
| **Optimizer** | AdamW (β₁=0.9, β₂=0.999) |
|
||
| **Learning Rate** | 2e-4 |
|
||
| **Batch Size** | 8 |
|
||
| **Epochs** | 3 |
|
||
| **Total Parameters** | ~3.8B |
|
||
|
||
### Dataset Composition
|
||
| Dataset Type | Samples | Purpose |
|
||
| :--- | :--- | :--- |
|
||
| Identity Alignment | 30 | Consistent persona training |
|
||
| SQL Generation | 300 | Structured query training |
|
||
| Instruction Tuning | 2,500 | General capability enhancement |
|
||
| Classification | 1,000 | Intent detection training |
|
||
|
||
---
|
||
|
||
## 💻 Quick Start
|
||
|
||
### Installation
|
||
```bash
|
||
pip install transformers torch accelerate
|
||
```
|
||
|
||
### Basic Usage (Text Generation)
|
||
```python
|
||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
import torch
|
||
|
||
model_id = "QuantaSparkLabs/Antiplex-instruct-3B"
|
||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_id,
|
||
torch_dtype=torch.float16,
|
||
device_map="auto"
|
||
)
|
||
|
||
prompt = "Write an SQL query to fetch users created in the last 30 days."
|
||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||
outputs = model.generate(
|
||
**inputs,
|
||
max_new_tokens=256,
|
||
temperature=0.7,
|
||
top_p=0.9,
|
||
do_sample=True,
|
||
pad_token_id=tokenizer.eos_token_id
|
||
)
|
||
|
||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||
```
|
||
|
||
### Classification Mode
|
||
```python
|
||
# Intent classification example
|
||
classification_prompt = """[CLASSIFY]
|
||
User Query: "I need to reset my account password"
|
||
Categories: account_issue, technical_support, billing, general_inquiry
|
||
"""
|
||
|
||
inputs = tokenizer(classification_prompt, return_tensors="pt").to(model.device)
|
||
outputs = model.generate(
|
||
**inputs,
|
||
max_new_tokens=64,
|
||
temperature=0.3,
|
||
do_sample=False
|
||
)
|
||
|
||
detected_intent = tokenizer.decode(outputs[0], skip_special_tokens=True).split('[')[-1].split(']')[0]
|
||
print(f"Detected Intent: {detected_intent}")
|
||
```
|
||
|
||
### Chat Interface
|
||
```python
|
||
from transformers import pipeline
|
||
|
||
chatbot = pipeline(
|
||
"text-generation",
|
||
model=model_id,
|
||
tokenizer=tokenizer,
|
||
device=0 if torch.cuda.is_available() else -1
|
||
)
|
||
|
||
messages = [
|
||
{"role": "system", "content": "You are Antiplex, a helpful AI assistant specialized in SQL and classification tasks."},
|
||
{"role": "user", "content": "Classify this intent: 'Can you help me with invoice generation?' Then write a SQL query to find recent invoices."}
|
||
]
|
||
|
||
response = chatbot(messages, max_new_tokens=512, temperature=0.7)
|
||
print(response[0]['generated_text'][-1]['content'])
|
||
```
|
||
|
||
---
|
||
|
||
## 🚀 Deployment Options
|
||
|
||
### Hardware Requirements
|
||
| Environment | VRAM | Quantization | Speed |
|
||
| :--- | :--- | :--- | :--- |
|
||
| **GPU (Optimal)** | 8-12 GB | FP16 | ⚡ Fast |
|
||
| **GPU (Efficient)** | 4-6 GB | INT8 | ⚡ Fast |
|
||
| **CPU** | N/A | FP32 | 🐌 Slow |
|
||
| **Edge Device** | 2-4 GB | INT4 | ⚡ Fast |
|
||
|
||
### Cloud Deployment (Docker)
|
||
```dockerfile
|
||
FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime
|
||
|
||
WORKDIR /app
|
||
COPY requirements.txt .
|
||
RUN pip install --no-cache-dir -r requirements.txt
|
||
|
||
COPY . .
|
||
EXPOSE 8000
|
||
|
||
CMD ["python", "app.py"]
|
||
```
|
||
|
||
---
|
||
|
||
## 📁 Repository Structure
|
||
```
|
||
Antiplex-Instruct-3B/
|
||
├── README.md
|
||
├── model.safetensors
|
||
├── config.json
|
||
├── tokenizer.json
|
||
├── tokenizer_config.json
|
||
├── generation_config.json
|
||
├── special_tokens_map.json
|
||
├── quantasparklogo.png
|
||
├── examples/
|
||
│ ├── classification_demo.py
|
||
│ ├── sql_generation_demo.py
|
||
│ └── chat_interface.py
|
||
└── evaluation/
|
||
└── test_results.json
|
||
```
|
||
|
||
---
|
||
|
||
## ⚠️ Limitations & Safety
|
||
|
||
### Known Limitations
|
||
- **Domain Specificity**: Not trained for medical/legal/safety-critical domains
|
||
- **Bias Inheritance**: May reflect biases in training data
|
||
- **Context Window**: Limited to 4K tokens
|
||
- **Multilingual**: Primarily English-focused
|
||
|
||
### Safety Guidelines
|
||
```python
|
||
# Recommended safety wrapper
|
||
def safety_check(text):
|
||
blocked_terms = ["harmful", "dangerous", "illegal", "exploit"]
|
||
if any(term in text.lower() for term in blocked_terms):
|
||
return "Content filtered for safety reasons."
|
||
return text
|
||
```
|
||
|
||
---
|
||
|
||
## 🔄 Version History
|
||
|
||
| Version | Date | Changes |
|
||
| :--- | :--- | :--- |
|
||
| v1.0.0 | 2026-01-1 | Initial release |
|
||
| v1.1.0 | 2026-01-10 | Enhanced classification head |
|
||
| v1.2.0 | 2026-01-25 | SQL generation improvements |
|
||
|
||
---
|
||
|
||
## 📄 License & Citation
|
||
|
||
**License:** Apache 2.0
|
||
|
||
**Citation:**
|
||
```bibtex
|
||
@misc{antiplex2026,
|
||
title={Antiplex-Instruct-3B: A Dual-Task Instruction-Tuned Language Model},
|
||
author={QuantaSparkLabs},
|
||
year={2026},
|
||
url={https://huggingface.co/QuantaSparkLabs/Antiplex-instruct-3B}
|
||
}
|
||
```
|
||
|
||
---
|
||
|
||
## 👥 Credits & Acknowledgments
|
||
|
||
- **Base Model**: Microsoft Phi-3 Mini team
|
||
- **Fine-tuning Framework**: Unsloth for efficient LoRA training
|
||
- **Evaluation**: Internal QuantaSparkLabs team
|
||
- **Testing**: Community contributors
|
||
|
||
---
|
||
|
||
## 🤝 Contributing & Support
|
||
|
||
### Reporting Issues
|
||
Please open an issue on our repository with:
|
||
1. Model version
|
||
2. Reproduction steps
|
||
3. Expected vs actual behavior
|
||
|
||
---
|
||
|
||
<p align="center">
|
||
<i>Built with ❤️ by QuantaSparkLabs</i><br/>
|
||
<sub>Model ID: Antiplex-Instruct-3B • Parameters: ~3.8B • Release: 2026</sub>
|
||
</p>
|
||
|
||
<p align="center">
|
||
<a href="https://github.com/unslothai/unsloth">
|
||
<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>
|
||
</a>
|
||
</p>
|
||
|
||
>Someone gimmi a cup of coffe!☕ |