初始化项目，由ModelHub XC社区提供模型

Model: QuantaSparkLabs/Antiplex-instruct-3B Source: Original Platform
2026-06-25 22:26:24 +08:00
commit b8555a8c3a
14 changed files with 277908 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,457 @@
+---
+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!☕
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 32000,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 32009,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "unsloth_version": "2026.5.5",
+  "use_cache": true,
+  "vocab_size": 32064
+}
--- a/evaluation/antiplex_metrics.json
+++ b/evaluation/antiplex_metrics.json
@@ -0,0 +1,19 @@
+{
+  "model_name": "QuantaSparkLabs/Antiplex-instruct-3B",
+  "performance": {
+    "identity_verification_accuracy": 1.0,
+    "sql_generation_accuracy": 1.0,
+    "general_reasoning_accuracy": 0.9,
+    "overall_grade": "B (Good)",
+    "test_dataset": "QuantaSparkLabs/antiplex-test-suite",
+    "total_tests": 21,
+    "passed_tests": 16
+  },
+  "training_details": {
+    "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+    "fine_tune_method": "LoRA (PEFT)",
+    "parameters": "3.8B",
+    "identity_examples": 30,
+    "sql_examples": 300
+  }
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "max_length": 4096,
+  "pad_token_id": 32009,
+  "transformers_version": "5.5.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d139f1b6b6e1356ae8601fdcd15fd20015e96fde2c6332b79b0d0fab11e6ff0
+size 7642192536
--- a/overview.png
+++ b/overview.png
--- a/quanta.png
+++ b/quanta.png
--- a/statics.png
+++ b/statics.png
--- a/structure.png
+++ b/structure.png
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,130 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|placeholder6|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    }
+  }
+}