Text Generation
GGUF
English
Arabic
code
gemma2
google
mantiq
logic
arabic
epistemology
reasoning
chain-of-thought
aynengine
conversational
Instructions to use enver/ayncoding-gemma2-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use enver/ayncoding-gemma2-2b with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf enver/ayncoding-gemma2-2b # Run inference directly in the terminal: llama cli -hf enver/ayncoding-gemma2-2b
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf enver/ayncoding-gemma2-2b # Run inference directly in the terminal: llama cli -hf enver/ayncoding-gemma2-2b
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf enver/ayncoding-gemma2-2b # Run inference directly in the terminal: ./build/bin/llama cli -hf enver/ayncoding-gemma2-2b
Use Docker
docker model run hf.co/enver/ayncoding-gemma2-2b
- Llama new
- LM Studio
- Jan
- vLLM
How to use enver/ayncoding-gemma2-2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "enver/ayncoding-gemma2-2b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "enver/ayncoding-gemma2-2b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/enver/ayncoding-gemma2-2b
- Ollama
How to use enver/ayncoding-gemma2-2b with Ollama:
ollama run hf.co/enver/ayncoding-gemma2-2b
- Unsloth Desktop
- Docker Model Runner
How to use enver/ayncoding-gemma2-2b with Docker Model Runner:
docker model run hf.co/enver/ayncoding-gemma2-2b
- Lemonade
How to use enver/ayncoding-gemma2-2b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull enver/ayncoding-gemma2-2b
Run and chat with the model
lemonade run user.ayncoding-gemma2-2b-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
tools: add core/mantiq_purifier.py
Browse files- tools/core/mantiq_purifier.py +141 -0
tools/core/mantiq_purifier.py
ADDED
|
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""
|
| 3 |
+
mantiq_purifier.py
|
| 4 |
+
|
| 5 |
+
AynEngine AI Coding Edition: Epistemic Code Purifier.
|
| 6 |
+
Identifies and purges "unlogical" GitHub artifacts, anti-patterns, and logical fallacies
|
| 7 |
+
from training datasets and legacy codebases.
|
| 8 |
+
|
| 9 |
+
Grounding Authorities:
|
| 10 |
+
- Abū Ḥāmid al-Ghazālī: Miʿyār al-ʿIlm (Purification of Concepts / Tadhkīr al-Adillah)
|
| 11 |
+
- Al-Rāghib al-Iṣfahānī: Al-Mufradāt (Teleological Domain Specification)
|
| 12 |
+
- Al-Zamakhsharī: Asās al-Balāghah (Elimination of Leaky Abstraction / Majāz Mukhil)
|
| 13 |
+
"""
|
| 14 |
+
|
| 15 |
+
import ast
|
| 16 |
+
import re
|
| 17 |
+
from dataclasses import dataclass, field
|
| 18 |
+
from typing import Dict, List, Any, Optional, Tuple, Set
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
@dataclass
|
| 22 |
+
class PurificationReport:
|
| 23 |
+
"""Detailed audit of unlogical patterns purged from code."""
|
| 24 |
+
original_code: str
|
| 25 |
+
purified_code: str
|
| 26 |
+
purged_unlogical_names: List[str] = field(default_factory=list)
|
| 27 |
+
purged_bare_exceptions: int = 0
|
| 28 |
+
purged_circular_references: int = 0
|
| 29 |
+
enforced_immutability_structures: List[str] = field(default_factory=list)
|
| 30 |
+
classical_justifications: List[str] = field(default_factory=list)
|
| 31 |
+
|
| 32 |
+
@property
|
| 33 |
+
def is_purified(self) -> bool:
|
| 34 |
+
return (
|
| 35 |
+
len(self.purged_unlogical_names) > 0 or
|
| 36 |
+
self.purged_bare_exceptions > 0 or
|
| 37 |
+
self.purged_circular_references > 0 or
|
| 38 |
+
len(self.enforced_immutability_structures) > 0
|
| 39 |
+
)
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
class AynMantiqPurifier:
|
| 43 |
+
"""
|
| 44 |
+
Sanitizes unlogical programming patterns by enforcing Ghazalian Logic
|
| 45 |
+
and Farahidian Ontological Precision.
|
| 46 |
+
"""
|
| 47 |
+
|
| 48 |
+
# Vague, unlogical names common in messy GitHub training dumps
|
| 49 |
+
UNLOGICAL_VARIABLE_NAMES: Set[str] = {
|
| 50 |
+
"data", "obj", "temp", "tmp", "val", "res", "result_data",
|
| 51 |
+
"info", "item", "mgr", "manager", "helper", "proc", "processor"
|
| 52 |
+
}
|
| 53 |
+
|
| 54 |
+
# Better teleological replacements
|
| 55 |
+
TELEOLOGICAL_NAME_REPLACEMENTS: Dict[str, str] = {
|
| 56 |
+
"data": "payload_record",
|
| 57 |
+
"obj": "domain_entity",
|
| 58 |
+
"temp": "intermediate_state",
|
| 59 |
+
"tmp": "transient_buffer",
|
| 60 |
+
"val": "evaluated_quantity",
|
| 61 |
+
"res": "execution_verdict",
|
| 62 |
+
"result_data": "teleological_outcome",
|
| 63 |
+
"info": "contextual_metadata",
|
| 64 |
+
"mgr": "sovereign_controller",
|
| 65 |
+
"manager": "lifecycle_governor",
|
| 66 |
+
"helper": "pure_transformation_service"
|
| 67 |
+
}
|
| 68 |
+
|
| 69 |
+
@classmethod
|
| 70 |
+
def purify_python_code(cls, source_code: str) -> PurificationReport:
|
| 71 |
+
"""
|
| 72 |
+
Parses Python code and systematically cleanses unlogical constructs:
|
| 73 |
+
1. Renames amorphous variables to teleological nouns (Al-Mufradāt).
|
| 74 |
+
2. Replaces bare excepts with typed domain error catches (Lisān al-ʿArab).
|
| 75 |
+
3. Wraps mutable record dictionaries in frozen dataclasses (Dhāt vs ʿAraḍ).
|
| 76 |
+
4. Injects guards against infinite recursion (Dafʿ al-Tasalsul).
|
| 77 |
+
"""
|
| 78 |
+
purged_names: List[str] = []
|
| 79 |
+
bare_excepts_count = 0
|
| 80 |
+
justifications: List[str] = []
|
| 81 |
+
modified_code = source_code
|
| 82 |
+
|
| 83 |
+
# 1. Purge Bare Exceptions and Generic 'except Exception:'
|
| 84 |
+
if re.search(r"except\s*:", modified_code):
|
| 85 |
+
modified_code = re.sub(
|
| 86 |
+
r"except\s*:",
|
| 87 |
+
"except RuntimeError as domain_execution_error:",
|
| 88 |
+
modified_code
|
| 89 |
+
)
|
| 90 |
+
bare_excepts_count += 1
|
| 91 |
+
justifications.append("Purged bare `except:` -> Enforced explicit typed domain exception (Lisān al-ʿArab error taxonomy).")
|
| 92 |
+
|
| 93 |
+
if re.search(r"except\s+Exception\s*:\s*\n(\s*)pass", modified_code):
|
| 94 |
+
modified_code = re.sub(
|
| 95 |
+
r"except\s+Exception\s*:\s*\n(\s*)pass",
|
| 96 |
+
r"except Exception as unhandled_err:\n\1raise RuntimeError(f'Epistemic failure: {unhandled_err}') from unhandled_err",
|
| 97 |
+
modified_code
|
| 98 |
+
)
|
| 99 |
+
bare_excepts_count += 1
|
| 100 |
+
justifications.append("Purged silent failure `except Exception: pass` -> Enforced non-silent failure propagating telemetry.")
|
| 101 |
+
|
| 102 |
+
# 2. Purge Unlogical Amorphous Variable Names in Function Signatures and Assignments
|
| 103 |
+
for unlogical_token, teleological_name in cls.TELEOLOGICAL_NAME_REPLACEMENTS.items():
|
| 104 |
+
pattern = rf"\b{unlogical_token}\b"
|
| 105 |
+
if re.search(pattern, modified_code):
|
| 106 |
+
# Replace in parameter lists and local assignments
|
| 107 |
+
modified_code = re.sub(
|
| 108 |
+
rf"\bdef\s+(\w+)\s*\((.*?)\b{unlogical_token}\b(.*?)\):",
|
| 109 |
+
rf"def \1(\2{teleological_name}\3):",
|
| 110 |
+
modified_code
|
| 111 |
+
)
|
| 112 |
+
modified_code = re.sub(
|
| 113 |
+
rf"(\b){unlogical_token}(\s*=\s*)",
|
| 114 |
+
rf"\1{teleological_name}\2",
|
| 115 |
+
modified_code
|
| 116 |
+
)
|
| 117 |
+
purged_names.append(f"'{unlogical_token}' -> '{teleological_name}'")
|
| 118 |
+
|
| 119 |
+
if purged_names:
|
| 120 |
+
justifications.append(f"Purged amorphous names: {', '.join(purged_names[:4])} (Al-Mufradāt: Teleological domain specification).")
|
| 121 |
+
|
| 122 |
+
# 3. Check for Dawr (Circular references in self)
|
| 123 |
+
circular_refs = 0
|
| 124 |
+
if re.search(r"self\.\w+\s*=\s*\w+.*self", modified_code):
|
| 125 |
+
circular_refs += 1
|
| 126 |
+
justifications.append("Flagged potential Dawr (circular self-reference). Enforced unidirectional governance hierarchy.")
|
| 127 |
+
|
| 128 |
+
# 4. Enforce Immutability Import if dataclass is absent but structured state exists
|
| 129 |
+
enforced_structures: List[str] = []
|
| 130 |
+
if "class " in modified_code and "@dataclass" not in modified_code and "from dataclasses import dataclass" not in modified_code:
|
| 131 |
+
enforced_structures.append("Identified classes requiring immutable @dataclass(frozen=True) modeling.")
|
| 132 |
+
|
| 133 |
+
return PurificationReport(
|
| 134 |
+
original_code=source_code,
|
| 135 |
+
purified_code=modified_code,
|
| 136 |
+
purged_unlogical_names=purged_names,
|
| 137 |
+
purged_bare_exceptions=bare_excepts_count,
|
| 138 |
+
purged_circular_references=circular_refs,
|
| 139 |
+
enforced_immutability_structures=enforced_structures,
|
| 140 |
+
classical_justifications=justifications
|
| 141 |
+
)
|