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

Property	Value
Model Name	Snapgate Surge V4
Model Type	LoRA Adapter
Base Model	Qwen3-14B Dense
Architecture	Transformer
Fine-tuning	LoRA
Framework	Unsloth
Trainer	TRL SFTTrainer
Languages	English, Indonesian
Context Length	2048 Tokens
License	Apache-2.0

🏢 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	Size
Snapgate	3B
Snapgate Code	4B
Snapgate Surge V1	7B
Snapgate Surge V2	10M
Snapgate Surge V3	7B Active (MoE)
Snapgate Surge V4	14B Dense

⚙️ Model Specifications

Specification	Value
Base Model	Qwen3-14B Dense
Fine-tuning	LoRA
Rank (r)	16
Alpha	32
Quantization	4-bit
Framework	Unsloth
Trainer	TRL SFTTrainer

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

Metric	Value
Framework	Unsloth
Trainer	TRL SFTTrainer
Total Steps	300
Completed	300 / 300 (100%)
Epochs	3
Initial Loss	1.7304
Final Loss	0.0124

Training Loss

Step	Loss
10	1.7304
20	0.4045
30	0.2602
40	0.1483
50	0.0915
60	0.0517
70	0.0316
80	0.0266
90	0.0250
100	0.0175
150	0.0152
200	0.0141
250	0.0135
300	0.0124

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

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

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for kadalicious22/snapgate-surge-v4

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B