Instructions to use enver/ayncoding-qwen2.5-coder-1.5b 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-qwen2.5-coder-1.5b 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-qwen2.5-coder-1.5b
# Run inference directly in the terminal:
llama cli -hf enver/ayncoding-qwen2.5-coder-1.5b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf enver/ayncoding-qwen2.5-coder-1.5b
# Run inference directly in the terminal:
llama cli -hf enver/ayncoding-qwen2.5-coder-1.5b

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-qwen2.5-coder-1.5b
# Run inference directly in the terminal:
./llama-cli -hf enver/ayncoding-qwen2.5-coder-1.5b

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-qwen2.5-coder-1.5b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf enver/ayncoding-qwen2.5-coder-1.5b

Use Docker

docker model run hf.co/enver/ayncoding-qwen2.5-coder-1.5b

LM Studio
Jan

vLLM

How to use enver/ayncoding-qwen2.5-coder-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "enver/ayncoding-qwen2.5-coder-1.5b"
# 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-qwen2.5-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/enver/ayncoding-qwen2.5-coder-1.5b

Ollama
How to use enver/ayncoding-qwen2.5-coder-1.5b with Ollama:
```
ollama run hf.co/enver/ayncoding-qwen2.5-coder-1.5b
```
Unsloth Desktop

How to use enver/ayncoding-qwen2.5-coder-1.5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf enver/ayncoding-qwen2.5-coder-1.5b

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "enver/ayncoding-qwen2.5-coder-1.5b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use enver/ayncoding-qwen2.5-coder-1.5b with Docker Model Runner:
```
docker model run hf.co/enver/ayncoding-qwen2.5-coder-1.5b
```

Lemonade

How to use enver/ayncoding-qwen2.5-coder-1.5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull enver/ayncoding-qwen2.5-coder-1.5b

Run and chat with the model

lemonade run user.ayncoding-qwen2.5-coder-1.5b-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use enver/ayncoding-qwen2.5-coder-1.5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf enver/ayncoding-qwen2.5-coder-1.5b

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default enver/ayncoding-qwen2.5-coder-1.5b

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use enver/ayncoding-qwen2.5-coder-1.5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf enver/ayncoding-qwen2.5-coder-1.5b

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "enver/ayncoding-qwen2.5-coder-1.5b" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

enver commited on Sep 8

Commit

2a784b6

verified ·

1 Parent(s): ff6d54f

feat: add sovereign Ollama Modelfile with 5 classical Arabic pillars

Browse files

Files changed (1) hide show

Modelfile +55 -0

Modelfile ADDED Viewed

	@@ -0,0 +1,55 @@

+FROM qwen2.5-coder:1.5b
+# Sovereign 5-Pillar Epistemic Hyperparameters (Optimized for 64-core 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 (ayncode): an elite, sovereign software synthesis and epistemic architectural engine.
+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.
+"""