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
File size: 8,759 Bytes
eca5751 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | """Task Planner - Lập kế hoạch cho multi-step tasks."""
from __future__ import annotations
from typing import List, Dict, Any, Optional
from dataclasses import dataclass, field
from enum import Enum
class TaskStatus(str, Enum):
PENDING = "pending"
IN_PROGRESS = "in_progress"
COMPLETED = "completed"
FAILED = "failed"
SKIPPED = "skipped"
@dataclass
class Task:
"""Một task trong plan."""
id: int
description: str
skill: Optional[str] = None
tools: List[str] = field(default_factory=list)
depends_on: List[int] = field(default_factory=list)
status: TaskStatus = TaskStatus.PENDING
result: Optional[str] = None
metadata: Dict[str, Any] = field(default_factory=dict)
@dataclass
class Plan:
"""Một execution plan."""
id: str
goal: str
tasks: List[Task] = field(default_factory=list)
created_at: str = ""
status: TaskStatus = TaskStatus.PENDING
def add_task(self, task: Task) -> None:
self.tasks.append(task)
def get_next_task(self) -> Optional[Task]:
"""Get next pending task whose dependencies are met.
v0.4 fix: out-of-range dep IDs are treated as UNMET (not silently ignored).
"""
for task in self.tasks:
if task.status != TaskStatus.PENDING:
continue
# Check dependencies
deps_met = True
for dep_id in task.depends_on:
if dep_id < 0 or dep_id >= len(self.tasks):
# Invalid dep ID → mark unmet, do NOT silently pass
deps_met = False
break
if self.tasks[dep_id].status not in (TaskStatus.COMPLETED, TaskStatus.SKIPPED):
deps_met = False
break
if deps_met:
return task
return None
def is_complete(self) -> bool:
return all(t.status in (TaskStatus.COMPLETED, TaskStatus.FAILED, TaskStatus.SKIPPED) for t in self.tasks)
def summary(self) -> Dict[str, Any]:
return {
"id": self.id,
"goal": self.goal,
"total_tasks": len(self.tasks),
"completed": sum(1 for t in self.tasks if t.status == TaskStatus.COMPLETED),
"failed": sum(1 for t in self.tasks if t.status == TaskStatus.FAILED),
"pending": sum(1 for t in self.tasks if t.status == TaskStatus.PENDING),
"is_complete": self.is_complete(),
}
class TaskPlanner:
"""Lập kế hoạch cho complex multi-step tasks.
Features:
- Decompose goal thành subtasks
- Identify dependencies
- Suggest skills/tools per task
- Track execution status
Usage:
planner = TaskPlanner()
plan = planner.create_plan("Build a REST API for todo app")
for task in plan.tasks:
print(f"Task {task.id}: {task.description}")
"""
def __init__(self):
self._plans: List[Plan] = []
self._next_plan_id = 1
def create_plan(self, goal: str) -> Plan:
"""Create an execution plan for a goal."""
plan = Plan(
id=f"plan_{self._next_plan_id}",
goal=goal,
created_at=__import__("datetime").datetime.now().isoformat(),
)
self._next_plan_id += 1
# Decompose goal into tasks
tasks = self._decompose(goal)
for i, task_def in enumerate(tasks):
task = Task(
id=i,
description=task_def["description"],
skill=task_def.get("skill"),
tools=task_def.get("tools", []),
depends_on=task_def.get("depends_on", []),
)
plan.add_task(task)
self._plans.append(plan)
return plan
def _decompose(self, goal: str) -> List[Dict[str, Any]]:
"""Decompose goal into subtasks.
This is a heuristic-based decomposition.
In production, this would use the LLM itself.
"""
goal_lower = goal.lower()
tasks = []
# Common patterns
if any(kw in goal_lower for kw in ["build", "create", "develop", "implement"]):
tasks.extend([
{
"description": f"Analyze requirements for: {goal}",
"skill": "reasoning",
"tools": [],
},
{
"description": "Design architecture and data models",
"skill": "algorithm_design",
"tools": [],
"depends_on": [0],
},
{
"description": "Implement core functionality",
"skill": "code_generation",
"tools": ["file_write", "python_exec"],
"depends_on": [1],
},
{
"description": "Write tests",
"skill": "testing",
"tools": ["python_exec", "shell_exec"],
"depends_on": [2],
},
{
"description": "Generate documentation",
"skill": "documentation",
"tools": ["file_write"],
"depends_on": [2],
},
{
"description": "Review and optimize code",
"skill": "code_review",
"tools": ["code_search", "code_lint"],
"depends_on": [3, 4],
},
])
elif any(kw in goal_lower for kw in ["debug", "fix", "repair"]):
tasks.extend([
{
"description": "Reproduce the issue",
"skill": "debugging",
"tools": ["shell_exec", "python_exec"],
},
{
"description": "Identify root cause",
"skill": "debugging",
"tools": ["code_search", "regex_search"],
"depends_on": [0],
},
{
"description": "Implement fix",
"skill": "code_generation",
"tools": ["file_write"],
"depends_on": [1],
},
{
"description": "Verify fix with tests",
"skill": "testing",
"tools": ["python_exec"],
"depends_on": [2],
},
])
elif any(kw in goal_lower for kw in ["analyze", "investigate", "understand"]):
tasks.extend([
{
"description": f"Gather information about: {goal}",
"skill": "reasoning",
"tools": ["web_search", "web_fetch", "file_read"],
},
{
"description": "Analyze and synthesize findings",
"skill": "data_analysis",
"tools": ["python_exec"],
"depends_on": [0],
},
{
"description": "Present insights and recommendations",
"skill": "summarization",
"tools": [],
"depends_on": [1],
},
])
else:
# Default: single task
tasks.append({
"description": f"Handle: {goal}",
"skill": None,
"tools": [],
})
return tasks
def execute_plan(
self,
plan: Plan,
executor=None,
) -> Plan:
"""Execute a plan step by step.
Args:
plan: Plan to execute
executor: Function(task) -> result (None = simulation)
"""
while not plan.is_complete():
task = plan.get_next_task()
if task is None:
break
task.status = TaskStatus.IN_PROGRESS
try:
if executor:
result = executor(task)
task.result = result
task.status = TaskStatus.COMPLETED
else:
task.status = TaskStatus.COMPLETED
task.result = "[simulated]"
except Exception as e:
task.status = TaskStatus.FAILED
task.result = f"Error: {e}"
return plan
def list_plans(self) -> List[Dict[str, Any]]:
"""List all plans."""
return [p.summary() for p in self._plans]
|