snapgate-surge-v4

Snapgate Surge V4

Official AI Assistant of Snapgate AI

Snapgate Surge V4 is a LoRA adapter built on top of Qwen3-14B (Dense) and instruction-tuned using proprietary conversational datasets developed by Snapgate AI.

---

✨ Highlights

• 🚀 Built on Qwen3-14B Dense
• ⚡ Fine-tuned using LoRA + Unsloth
• 💻 Optimized for coding assistance
• 🇮🇩 Native support for Indonesian & English
• 🧠 Strong instruction-following capability
• 📉 Final training loss: 0.0124
• 🤖 Official AI Assistant of Snapgate AI
• 🔓 Apache 2.0 Licensed LoRA Adapter

---

📖 Model Overview

---

🏢 About Snapgate AI

Snapgate AI is an AI platform focused on building intelligent assistants for programming, productivity, research, and everyday tasks.

The Snapgate ecosystem includes multiple AI products:

• 🤖 Snapgate Lite
• 🚀 Snapgate Titan
• 🧠 Cognira
• 📄 Ask PDF
• 💻 Online Code Editor
• 📝 AI Report Summarizer
• 🩺 Lexar AI
• 🎨 Frontend Generator

Users receive 50,000 free tokens every day.

🌐 Website

https://snapgate.tech

---

📚 Snapgate Model Family

---

⚙️ Model Specifications

Target Modules

• q_proj
• k_proj
• v_proj
• o_proj
• gate_proj
• up_proj
• down_proj

---

✨ Capabilities

✔ Programming Assistance

• Python
• PHP
• JavaScript
• TypeScript
• C++
• Java
• HTML/CSS
• SQL

✔ Web Development

✔ Debugging

✔ Technical Writing

✔ General Question Answering

✔ Instruction Following

✔ Bilingual Conversations

✔ Long-form Explanations

---

📈 Training Progress

The model was instruction-tuned using Unsloth and TRL SFTTrainer.

Training Summary

Training Loss

Training Notes

• ✅ Successfully completed all scheduled training steps.
• 📉 Stable convergence throughout training.
• 💾 Periodic checkpoints were saved to support training resumption.
• ⚡ Optimized using Unsloth for efficient fine-tuning.

---

📦 Repository Contents

This repository contains:

• ✅ LoRA adapter
• ✅ Adapter configuration
• ✅ Tokenizer configuration
• ✅ Generation configuration
• ✅ Model Card

This repository DOES NOT contain the Qwen3-14B base model.

---

📋 Requirements

Install dependencies:

pip install unsloth transformers peft accelerate bitsandbytes

Recommended versions:

• transformers >= 4.52
• peft >= 0.16
• torch >= 2.6
• unsloth

---

🚀 Quick Start

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="kadalicious22/snapgate-surge-v4",
    max_seq_length=2048,
    load_in_4bit=True,
)

FastLanguageModel.for_inference(model)

messages = [
    {
        "role": "system",
        "content": "You are Surge, an AI assistant developed by Snapgate AI."
    },
    {
        "role": "user",
        "content": "Who are you?"
    }
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
).to("cuda")

outputs = model.generate(
    input_ids=inputs,
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.9,
)

print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))

---

🔧 Loading the LoRA Adapter

This repository contains only the LoRA adapter.

Download the Qwen3-14B base model and load the adapter:

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/Qwen3-14B",
    max_seq_length=2048,
    load_in_4bit=True,
)

model.load_adapter("kadalicious22/snapgate-surge-v4")

FastLanguageModel.for_inference(model)

---

🔀 Merge the Adapter

To create a standalone model:

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/Qwen3-14B",
    load_in_4bit=False,
)

model.load_adapter("kadalicious22/snapgate-surge-v4")

model = model.merge_and_unload()

model.save_pretrained_merged(
    "snapgate-surge-v4-merged",
    tokenizer,
    save_method="merged_16bit",
)

Load the merged model normally:

from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "snapgate-surge-v4-merged"
)

model = AutoModelForCausalLM.from_pretrained(
    "snapgate-surge-v4-merged",
    torch_dtype="auto",
    device_map="auto",
)

---

🌐 Snapgate API

curl https://snapgate.tech/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model":"snapgate-lite",
"messages":[
{
"role":"user",
"content":"Hello!"
}
]
}'

---

📊 Training Details

• Base Model: Qwen3-14B Dense
• Fine-tuning: LoRA
• Framework: Unsloth
• Trainer: TRL SFTTrainer
• Dataset: Proprietary Snapgate AI conversational dataset
• Languages: English & Indonesian
• Focus:
  • Coding
  • Instruction Following
  • Technical Assistance
  • General Conversations

---

⚠️ Notes

This repository only contains the LoRA adapter.

To use the model, you must first obtain the original Qwen3-14B base model and then load this adapter using PEFT or Unsloth.

---

📄 License

Released under the Apache 2.0 License.

The Qwen3-14B base model remains subject to its original license.

---

📚 Citation

@misc{snapgate2026surgev4,
  title={Snapgate Surge V4},
  author={Snapgate AI},
  year={2026},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/kadalicious22/snapgate-surge-v4}}
}

---

🔗 Links

Website

https://snapgate.tech

About

https://snapgate.tech/about.html

Hugging Face

https://huggingface.co/kadalicious22

Instagram

https://instagram.com/snapgate.ai

Discord

https://discord.gg/HBBCzb5VY8

Base Model

https://huggingface.co/unsloth/Qwen3-14B

---

⭐ If you find Snapgate Surge V4 useful, consider giving the repository a Star ❤️ on Hugging Face to support future development.