Instructions to use Neura-Tech-AI/Neuron-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neura-Tech-AI/Neuron-4B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Neura-Tech-AI/Neuron-4B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neura-Tech-AI/Neuron-4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Neura-Tech-AI/Neuron-4B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Neura-Tech-AI/Neuron-4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neura-Tech-AI/Neuron-4B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neura-Tech-AI/Neuron-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-4B-Instruct

SGLang

How to use Neura-Tech-AI/Neuron-4B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Neura-Tech-AI/Neuron-4B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neura-Tech-AI/Neuron-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Neura-Tech-AI/Neuron-4B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neura-Tech-AI/Neuron-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neura-Tech-AI/Neuron-4B-Instruct with Docker Model Runner:
```
docker model run hf.co/Neura-Tech-AI/Neuron-4B-Instruct
```

Neura-Tech-AI commited on 5 days ago

Commit

22e6e13

verified ·

1 Parent(s): bd78a9f

Update README.md

Browse files

Files changed (1) hide show

README.md +193 -4

README.md CHANGED Viewed

@@ -1,7 +1,196 @@
 ---
 license: apache-2.0
-base_model:
-- Qwen/Qwen3-4B-Instruct-2507
 pipeline_tag: text-generation
-library_name: transformers
----

 ---
+library_name: transformers
 license: apache-2.0
+base_model: Qwen/Qwen3-4B-Instruct-2507
 pipeline_tag: text-generation
+language:
+- en
+- hi
+- zh
+- ja
+- ko
+- fr
+- de
+- es
+- it
+- pt
+- ru
+- ar
+- tr
+- vi
+- th
+- id
+- ms
+- bn
+- ta
+- te
+- mr
+- gu
+- pa
+- ur
+- fa
+tags:
+- Neura Tech AI
+- neuron
+- instruct
+- llm
+- transformer
+- qwen
+- multilingual
+- conversational
+- coding
+new_version: Neura-Tech-AI/Neuron-V2-4B-Instruct
+---
+# Neuron-V2-4B-Instruct
+> A multilingual instruction-tuned large language model developed by **Neura Tech AI**.
+---
+# Overview
+**Neuron-V2-4B-Instruct** is an instruction-tuned language model built on top of **Qwen/Qwen3-4B-Instruct-2507**.
+The goal of Neuron is to provide a powerful open-source AI assistant capable of natural conversations, coding assistance, reasoning, multilingual understanding, and long-context processing.
+---
+# Developer
+**Developed by**
+- Neura Tech AI
+---
+# Base Model
+**Base Model**
+Qwen/Qwen3-4B-Instruct-2507
+We sincerely thank the Qwen Team for releasing the Qwen3 model family under the Apache 2.0 License.
+---
+# Model Details
+- **Model Name:** Neuron-V2-4B-Instruct
+- **Developer:** Neura Tech AI
+- **Base Model:** Qwen/Qwen3-4B-Instruct-2507
+- **Architecture:** Transformer Decoder
+- **Parameters:** ~4 Billion
+- **Context Length:** 262,144 Tokens (Inherited from the base model)
+- **License:** Apache-2.0
+---
+# Features
+- Instruction Following
+- Chat Assistant
+- Coding Assistance
+- Mathematical Reasoning
+- Logical Reasoning
+- Long Context Support
+- Tool Calling Support
+- Multilingual Understanding
+- Creative Writing
+- General Knowledge
+- Open-source
+---
+# Supported Languages
+Neuron inherits multilingual capabilities from the Qwen3 base model and supports many languages, including:
+- English
+- Hindi
+- Chinese
+- Japanese
+- Korean
+- French
+- German
+- Spanish
+- Italian
+- Portuguese
+- Russian
+- Arabic
+- Turkish
+- Vietnamese
+- Thai
+- Indonesian
+- Malay
+- Bengali
+- Tamil
+- Telugu
+- Marathi
+- Gujarati
+- Punjabi
+- Urdu
+- Persian (Farsi)
+and many more.
+---
+# Benchmark Results
+| Benchmark | Score |
+|-----------|-------|
+| MMLU | **70.61** |
+| ARC Challenge | **55.89** |
+| HellaSwag | **52.64** |
+| Winogrande | **67.88** |
+| PIQA | **76.01** |
+| BoolQ | **84.77** |
+| TruthfulQA MC1 | **42.84** |
+| TruthfulQA MC2 | **62.59** |
+### MMLU Category Scores
+| Category | Score |
+|----------|------:|
+| Humanities | 60.83 |
+| Social Sciences | 80.37 |
+| STEM | 71.61 |
+| Other | 74.73 |
+---
+# Intended Use
+**Neuron-V2-4B-Instruct** is suitable for:
+- AI Assistants
+- Chatbots
+- Coding
+- Education
+- Research
+- Content Writing
+- Translation
+- Reasoning Tasks
+- Tool Calling
+- General NLP Applications
+---
+# License
+This model is released under the **Apache-2.0 License** inherited from the base model.
+Please also comply with the Qwen model license and usage guidelines.
+---
+# Acknowledgements
+This project is built upon the excellent **Qwen3 model family** released by the **Qwen Team**.
+We sincerely thank the **Qwen Team** and the open-source AI community for making this project possible.
+---
+# © 2026 Neura Tech AI. All rights reserved.