Instructions to use AdminReal/NexusCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdminReal/NexusCoder with Transformers:

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

pipe = pipeline("text-generation", model="AdminReal/NexusCoder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdminReal/NexusCoder")
model = AutoModelForCausalLM.from_pretrained("AdminReal/NexusCoder", 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 AdminReal/NexusCoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AdminReal/NexusCoder

SGLang

How to use AdminReal/NexusCoder 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 "AdminReal/NexusCoder" \
    --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": "AdminReal/NexusCoder",
		"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 "AdminReal/NexusCoder" \
        --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": "AdminReal/NexusCoder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdminReal/NexusCoder with Docker Model Runner:
```
docker model run hf.co/AdminReal/NexusCoder
```

NexusCoder / configs /nexus_coder_tiny.yaml

AdminReal

Import NexusCoder from github.com/mhieuhonda/NexusCoder

eca5751 verified about 1 month ago

Raw

History Blame Contribute Delete

1.61 kB

	# Nexus Coder Configuration - Tiny version v0.3
	# Used for quick verification on CPU (~5M params)
	# Author: Hieu Louis (2026)

	model:
	name: "Nexus Coder Tiny"
	agent_name: "Nexus"
	author: "Hieu Louis"
	version: "0.3.0-tiny"
	github: "mhieuhonda"
	year: "2026"

	architecture:
	vocab_size: 2000
	hidden_size: 256
	num_hidden_layers: 4
	num_attention_heads: 8
	num_kv_heads: 2
	head_dim: 32
	intermediate_size: 512
	hidden_act: "silu"
	norm_type: "rmsnorm"

	moe:
	num_experts: 4
	num_active_experts: 2
	router_aux_loss_coef: 0.001
	router_jitter_noise: 0.0

	context:
	max_position_embeddings: 512
	rotary_emb_base: 10000.0
	rope_scaling_type: null
	rope_scaling_factor: 1.0

	# v0.3 NEW architecture features (most OFF for tiny — too small to benefit)
	attention:
	use_flash_attention: false
	use_flash_attention_2: false
	use_alibi: false
	use_sliding_window: false
	sliding_window_size: 256
	use_qk_norm: false
	mlp_parallel: true

	compute:
	use_kv_cache: true
	kv_cache_quantization: null
	gradient_checkpointing: false

	params:
	total: "~8M (demo only)"
	active: "~5M"
	note: "For testing only. Use nexus_coder_10b.yaml for the real model."

	training:
	learning_rate: 5.0e-4
	weight_decay: 0.01
	warmup_steps: 10
	max_steps: 30
	per_device_batch_size: 2
	gradient_accumulation_steps: 1
	logging_steps: 5
	save_steps: 30

	inference:
	max_new_tokens: 50
	temperature: 0.8
	top_k: 50
	top_p: 0.9
	do_sample: true

	personality:
	type: "humorous"
	language: "bilingual"

	environment:
	python_version: "3.12.13"
	pytorch_version: ">=2.0"
	cuda_required: false