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 / scripts /count_params.py

AdminReal

Import NexusCoder from github.com/mhieuhonda/NexusCoder

eca5751 verified about 1 month ago

Raw

History Blame Contribute Delete

2.28 kB

	"""
	Script đếm tham số Nexus Coder 10B / 1.5B active
	=================================================
	Chạy: python scripts/count_params.py
	"""
	import sys
	import os
	sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

	from nexus.config import NexusConfig, print_config_summary


	def main():
	"""In tóm tắt cấu hình và tham số."""
	config = NexusConfig()
	print_config_summary(config)

	stats = config.estimated_total_params()

	print("\n📋 Chi tiết tính toán tham số:")
	print(f" Embedding (vocab×hidden): {stats['embedding']:,} ({stats['embedding']/1e6:.1f}M)")
	print(f" Attention per layer: {stats['attention_per_layer']:,} ({stats['attention_per_layer']/1e6:.1f}M)")
	print(f" MoE per layer (total): {stats['moe_total_per_layer']:,} ({stats['moe_total_per_layer']/1e6:.1f}M)")
	print(f" MoE per layer (active): {stats['moe_active_per_layer']:,} ({stats['moe_active_per_layer']/1e6:.1f}M)")
	print(f" Router per layer: {stats['router_per_layer']:,}")
	print(f" Per layer (total): {stats['per_layer_total']:,} ({stats['per_layer_total']/1e6:.1f}M)")
	print(f" Per layer (active): {stats['per_layer_active']:,} ({stats['per_layer_active']/1e6:.1f}M)")
	print(f" Số layers: {stats['total_layers']}")
	print()
	print(f" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━")
	print(f" Tổng tham số: {stats['total_params']:>15,} ({stats['total_params_billion']:.2f}B)")
	print(f" Tham số active:{stats['active_params']:>15,} ({stats['active_params_billion']:.2f}B)")
	print(f" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━")

	# Verify
	assert 9.5e9 < stats["total_params"] < 11e9, "❌ Total params không đúng (phải ~10B)"
	assert 1.3e9 < stats["active_params"] < 1.7e9, "❌ Active params không đúng (phải ~1.5B)"
	print("\n✅ Đã xác nhận: 10B tổng tham số / 1.5B tham số active - đúng theo yêu cầu!")


	if __name__ == "__main__":
	main()