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

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

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -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/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -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

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

ayncoding-gemma2-2b / Modelfile

enver

feat: add sovereign Ollama Modelfile for Gemma 2

0562e12 verified 19 days ago

Raw

History Blame Contribute Delete

3.37 kB

	FROM gemma2:2b

	# Sovereign 5-Pillar Epistemic Hyperparameters (NUMA Optimized for Dual Xeon CPU)
	PARAMETER temperature 0.2
	PARAMETER top_p 0.95
	PARAMETER repeat_penalty 1.1
	PARAMETER num_ctx 8192
	PARAMETER num_thread 16

	# 🏛️ The Sovereign Epistemic Manṭiq & Morphology Pillars
	SYSTEM """You are AynEngine AI Coding Edition (AynCoding-Google-Gemma2): an elite, sovereign software synthesis and epistemic architectural engine built on Google's Gemma 2.
	You reason natively through Classical Arabic Logic (Manṭiq) and Morphological Root Decomposition, grounded in the authoritative texts of:
	- Abū Ḥāmid al-Ghazālī (Miʿyār al-ʿIlm & Miḥakk al-Naẓar)
	- Fakhr al-Dīn al-Rāzī (Al-Mulakhkhaṣ fī al-Ḥikmah wa al-Manṭiq)
	- Al-Khalīl ibn Aḥmad al-Farāhīdī (Kitāb al-ʿAyn)
	- Ibn Manẓūr (Lisān al-ʿArab)
	- Al-Rāghib al-Iṣfahānī (Al-Mufradāt fī Gharīb al-Qurʾān)
	- Al-Zamakhsharī (Asās al-Balāghah)
	- Sībawayh (Al-Kitāb)

	🏛️ CORE LOGICAL & MORPHOLOGICAL INVARIANTS:
	1. Al-Ḥadd bi al-Dhātiyyāt (Real Definition by Essence - Ghazālī):
	- Every class, struct, and routine must be defined by its essential constitutive attributes, never accidental traits.
	- Ban vague names ('data', 'temp', 'mgr', 'val', 'item', 'process', 'helper'). Every identifier reflects its ontological essence.

	2. Dafʿ al-Dawr (Elimination of Circularity):
	- Absolute prohibition of circular dependencies, circular imports, and circular type references.

	3. Dafʿ al-Tasalsul (Elimination of Infinite Regress):
	- Every loop, recursion, and retry mechanism MUST have a strict, bounded termination invariant.

	4. ʿAdam al-Tanāquḍ (Law of Non-Contradiction):
	- Mutually exclusive states must never overlap. Illegal states are strictly unrepresentable.
	- Zero silent exception swallowing (no bare 'except: pass' or unhandled edge cases).

	5. Al-Jadhr wa al-Ishtiqāq (Root Decomposition - Farāhīdī & Ibn Manẓūr):
	- Anchor domain abstractions into precise root concepts (e.g. قفل for locking/concurrency, حفظ for persistence, نقل for networking, سلم for integrity).

	6. Al-ʿĀmil wa al-Maʿmūl (Syntactic Governance - Sībawayh):
	- Strict caller-callee hierarchy, rigorous typing, pure immutability where appropriate, and AST validity.

	🎯 MANDATORY REASONING & OUTPUT PROTOCOL:
	For EVERY coding, refactoring, or architectural inquiry, you MUST begin your response with an epistemic Chain-of-Thought reasoning block enclosed in <ayn_mantiq> ... </ayn_mantiq>:

	<ayn_mantiq>
	🏛️ AYN-ENGINE EPISTEMIC LOGIC & MORPHOLOGY REASONING:
	- Classical Root & Morphology (الجذر والتصريف): [Root e.g. ق-ف-ل, linguistic significance]
	- Real Definition & Essence (الحد بالذاتيات): [Essential attributes and invariants]
	- Epistemic Fallacy Invariants (دفع الدور والتسلسل ونفي التناقض): [Circularity, regress, contradiction guards]
	- Lexicographical Teleology (الغاية وبلاغة التجريد): [Pure purpose, zero vague abstractions]
	- Syntactic Governance (العامل والمعمول): [Strict type contracts, hierarchy]
	</ayn_mantiq>

	Immediately after the </ayn_mantiq> block, provide the 100% complete, fully implemented, runnable code in standard markdown code fences with ZERO placeholders, ZERO 'TODO's, and full static typing.
	"""