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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neura-Tech-AI/Nexa-AI-4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Neura-Tech-AI/Nexa-AI-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Neura-Tech-AI/Nexa-AI-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/Nexa-AI-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/Nexa-AI-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Neura-Tech-AI/Nexa-AI-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/Nexa-AI-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/Nexa-AI-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/Nexa-AI-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/Nexa-AI-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Neura-Tech-AI commited on Jul 12

Commit

b46292b

verified ·

1 Parent(s): ca553d5

Update README.md

Browse files

Files changed (1) hide show

README.md +43 -25

README.md CHANGED Viewed

@@ -1,8 +1,7 @@
 ---
 library_name: transformers
-base_model: Qwen/Qwen3-4B-Instruct-2507
 license: apache-2.0
-license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
 pipeline_tag: text-generation
 language:
 - en
@@ -10,43 +9,62 @@ language:
 - zh
 ---
-# Nexa AI
-> Nexa AI is a collaborative large language model developed by **Neura Tech AI** and **Lumina AI**.
 ## Overview
-Nexa AI is an instruction-tuned language model built on top of **Qwen3-4B-Instruct-2507**. It extends the capabilities of the base model with additional fine-tuning focused on multilingual conversations, coding, mathematics, reasoning, agentic workflows, tool calling, and improved instruction following.
-### Base Model
-- **Base Model:** Qwen/Qwen3-4B-Instruct-2507
-- **Architecture:** Qwen3
-- **Parameters:** 4B
-- **License:** Apache-2.0
-## Developed By
-**Neura Tech AI × Lumina AI**
-Nexa AI is a joint collaborative project created by Neura Tech AI and Lumina AI.
-## Improvements
-- Better multilingual conversations
-- Improved Hindi support
-- Stronger coding performance
-- Better mathematical reasoning
-- Enhanced tool calling
-- Optimized for agentic workflows
-- Improved instruction following
-- Fine-tuned identity and behavior
-- Better response quality
-## Acknowledgements
-Nexa AI is built upon the excellent **Qwen3-4B-Instruct-2507** model released by the Qwen Team. We sincerely thank the Qwen Team for making the base model available under the Apache-2.0 License.
 ## Model Overview
 **Qwen3-4B-Instruct-2507** has the following features:

 ---
 library_name: transformers
 license: apache-2.0
+base_model: Qwen/Qwen3-4B-Instruct-2507
 pipeline_tag: text-generation
 language:
 - en
 - zh
 ---
+# Nexa-AI-4B-Instruct
+> A collaborative open-source large language model developed by **Neura Tech AI** and **Lumina AI**.
 ## Overview
+**Nexa-AI-4B-Instruct** is an instruction-tuned large language model built on top of **Qwen/Qwen3-4B-Instruct-2507**.
+This project is jointly developed by:
+- **Neura Tech AI**
+- **Lumina AI**
+Nexa AI focuses on delivering a capable multilingual AI assistant with strong performance in:
+- General conversation
+- Instruction following
+- Coding
+- Mathematics
+- Logical reasoning
+- Tool calling & AI agents
+- Multilingual understanding (including English, Hindi, Chinese, and more)
+## 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, which made this project possible.
+## Developers
+**Project:** Nexa AI
+**Developed by:**
+- Neura Tech AI
+- Lumina AI
+## Model Details
+- Model Name: **Nexa-AI-4B-Instruct**
+- 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 (Base model license)
+## Features
+- High-quality instruction following
+- Coding assistance
+- Mathematical reasoning
+- Agent & tool calling support
+- Multilingual capabilities
+- Long-context understanding
+- Fine-tuned alignment for helpful responses
+-
 ## Model Overview
 **Qwen3-4B-Instruct-2507** has the following features: