Text Generation
Transformers
Safetensors
qwen2
coder
code
agent
conversational
text-generation-inference
Instructions to use AdminReal/NexusCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
| """ | |
| Code Minifier Tool - Minify JS/CSS/HTML code. | |
| Author: Hieu Louis (2026) | |
| Lazy import: | |
| - JavaScript : `jsmin` | |
| - CSS : `cssmin` | |
| - HTML : `htmlmin` | |
| MODERATE safety (in-place edit possible), requires_confirmation. | |
| """ | |
| from __future__ import annotations | |
| from typing import Any, Dict, Optional | |
| from .base import Tool, ToolResult, ToolContext, ToolCategory, ToolSafety | |
| SUPPORTED_LANGS = {"javascript", "css", "html"} | |
| class CodeMinifierTool(Tool): | |
| """Minify JavaScript/CSS/HTML code (lazy deps).""" | |
| category = ToolCategory.CODE | |
| safety = ToolSafety.MODERATE # in-place edit | |
| requires_confirmation = True | |
| def name(self) -> str: | |
| return "code_minifier" | |
| def description(self) -> str: | |
| return ( | |
| "Minify code JS/CSS/HTML. Sử dụng jsmin (JS), cssmin (CSS), htmlmin (HTML). " | |
| "In-place edit nếu cung cấp path. Trả về reduction %." | |
| ) | |
| def parameters(self) -> Dict[str, Any]: | |
| return { | |
| "type": "object", | |
| "properties": { | |
| "path": {"type": "string", "description": "File để minify (in-place)"}, | |
| "code": {"type": "string", "description": "Code để minify (nếu không dùng path)"}, | |
| "language": { | |
| "type": "string", | |
| "enum": sorted(SUPPORTED_LANGS), | |
| "description": "Ngôn ngữ: javascript/css/html", | |
| }, | |
| }, | |
| "anyOf": [{"required": ["path"]}, {"required": ["code"]}], | |
| "required": ["language"], | |
| } | |
| def validate_args(self, args: Dict[str, Any]) -> Optional[str]: | |
| lang = args.get("language") | |
| if not lang: | |
| return "Missing required arg: language" | |
| if lang not in SUPPORTED_LANGS: | |
| return f"Unsupported language: {lang}. Chọn: {sorted(SUPPORTED_LANGS)}" | |
| if not args.get("path") and not args.get("code"): | |
| return "Missing required arg: path hoặc code" | |
| return None | |
| def execute(self, args: Dict[str, Any], context: ToolContext) -> ToolResult: | |
| lang: str = args["language"] | |
| path = args.get("path") | |
| code: Optional[str] = args.get("code") | |
| if path: | |
| if context.dry_run: | |
| return ToolResult( | |
| success=True, | |
| output=f"[dry-run] Sẽ minify {path} ({lang})", | |
| metadata={"path": path, "language": lang, "dry_run": True}, | |
| ) | |
| try: | |
| with open(path, "r", encoding="utf-8") as f: | |
| code = f.read() | |
| except Exception as e: | |
| return ToolResult(success=False, error=f"Đọc file lỗi: {e}", return_code=1) | |
| assert code is not None | |
| try: | |
| if lang == "javascript": | |
| try: | |
| import jsmin # type: ignore | |
| except ImportError as e: | |
| return ToolResult( | |
| success=False, | |
| error=f"jsmin not installed: {e}. Cài: pip install jsmin", | |
| return_code=127, | |
| ) | |
| minified = jsmin.jsmin(code) | |
| elif lang == "css": | |
| try: | |
| import cssmin # type: ignore | |
| except ImportError as e: | |
| return ToolResult( | |
| success=False, | |
| error=f"cssmin not installed: {e}. Cài: pip install cssmin", | |
| return_code=127, | |
| ) | |
| minified = cssmin.cssmin(code) | |
| elif lang == "html": | |
| try: | |
| import htmlmin # type: ignore | |
| except ImportError as e: | |
| return ToolResult( | |
| success=False, | |
| error=f"htmlmin not installed: {e}. Cài: pip install htmlmin", | |
| return_code=127, | |
| ) | |
| minifier = htmlmin.Minifier( | |
| remove_comments=True, | |
| remove_empty_space=True, | |
| remove_optional_attribute_quotes=False, | |
| ) | |
| minified = minifier.minify(code) | |
| else: | |
| return ToolResult(success=False, error=f"Unsupported language: {lang}", return_code=1) | |
| except Exception as e: | |
| return ToolResult(success=False, error=f"{type(e).__name__}: {e}", return_code=1) | |
| # Write back if path provided | |
| artifacts = [] | |
| if path: | |
| try: | |
| with open(path, "w", encoding="utf-8") as f: | |
| f.write(minified) | |
| artifacts.append(path) | |
| except Exception as e: | |
| return ToolResult(success=False, error=f"Write file lỗi: {e}", return_code=1) | |
| ratio = (len(minified) / max(1, len(code))) * 100.0 | |
| return ToolResult( | |
| success=True, | |
| output=minified, | |
| artifacts=artifacts, | |
| metadata={ | |
| "language": lang, | |
| "path": path, | |
| "input_length": len(code), | |
| "output_length": len(minified), | |
| "reduction_pct": round(100.0 - ratio, 2), | |
| "in_place": bool(path), | |
| }, | |
| ) | |