Instructions to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 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 Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
# Run inference directly in the terminal:
llama cli -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
# Run inference directly in the terminal:
llama cli -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

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 Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
# Run inference directly in the terminal:
./llama-cli -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

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 Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

Use Docker

docker model run hf.co/Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

LM Studio
Jan

vLLM

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

Ollama
How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with Ollama:
```
ollama run hf.co/Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
```
Unsloth Desktop

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

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": "Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with Docker Model Runner:
```
docker model run hf.co/Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16
```

Lemonade

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

Run and chat with the model

lemonade run user.qwen3loop-0.6b-sft-deep-supervision-v1-F16

List all available models

lemonade list

Hermes Agent

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

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 Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16

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 "Lordnyx/qwen3loop-0.6b-sft-deep-supervision-v1:F16" \
  --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"

Qwen3Loop-0.6B-SFT-Deep-Supervision (v1.0 Production: Eurus-2 + Open-R1 CoT & Adaptive Halting)

Qwen3Loop-0.6B is a state-of-the-art recursive reasoning language model utilizing recurrent looped layers to achieve the reasoning density and depth of a ~2B parameter model within a 0.6B physical parameter footprint.

🌟 Core Architecture & Innovation

Physical Parameters: 28 transformer blocks (hidden_size: 1024, intermediate_size: 3072, heads: 16).
LoopSplit Architecture:
- Prefix: Layers 0..6 (computed once).
- Middle Stack (Miolo): Layers 7..20 (computed 3 times recurrently = 42 layer passes).
- Suffix: Layers 21..27 (computed once).
- Total Logical Depth: 56 layers ($7 + 14 \times 3 + 7 = 56$).
Curated Multi-Phase Dataset: Fine-tuned on 6,324 strictly filtered and curated samples (25.3 MB) from PRIME-RL/Eurus-2-SFT-Data (agentic multi-phase) and open-r1/Mixture-of-Thoughts (coding CoT), annotated across 9 meta-supervision dimensions with convaiinnovations/laya.
Adaptive Halting Probe: Includes latent_halting_probe.pt, an ultralight MLP head trained directly on intermediate prompt prefill states to decide optimal exit depth with 91.5% classification accuracy.

📊 Training & Validation Metrics

Metric	Result	Context / Meaning
Validation Loss	`0.4012`	Down from `0.6705` (smooth, stable convergence)
Perplexity (PPL)	`1.49`	Near-optimal linguistic and logical fluency
Hardware Stability	5.58 GB VRAM	Flat VRAM curve throughout 375 steps on RTX 3060 12GB
Halting Probe Routing Acc	`91.5%`	Calibrated on prompt prefill representations (MSE: `0.0015`)

🥊 Direct Confrontation: Base 28-Layer vs Qwen3Loop 56-Layer Unrolled

Evaluated under identical sampling parameters (temperature=0.1, Q8_0 quantization on RTX 3060):

Challenge Task	Base Unsloth (`Qwen3-0.6B-Q8_0`) [28L]	Qwen3Loop SFT (`unrolled_q8_0`) [56L]	Outcome
Modular Arithmetic ($2^{100} \pmod 7$)	Incomplete / Verbose divergence (Overflowed token budget without answer)	Exact: $\boxed{2}$ in 5 logical steps (Detected optimal order $2^3 \equiv 1 \pmod 7$)	🟢 Qwen3Loop
Deductive Logic (Sally Siblings Riddle)	Trapped in self-doubt loop	Deduced correct sister relationship	🟢 Qwen3Loop
Linguistic Trick (17 sheep, all but 9 die)	Arithmetic subtraction error ($17-9=8$)	Arithmetic subtraction error ($17-9=8$)	⚪ Tie
Power Cycles (Units digit of $3^{2025}$)	Stopped at cycle definition	Full sequence & pattern $(3,9,7,1)$	🟢 Qwen3Loop
Algorithm Formulation (Balanced Parentheses)	Drafted stack concept, cut off	Counter-based $O(n)$ time / $O(1)$ space logic	🟢 Qwen3Loop
Generation Speed	255.6 tokens/s (28 layers)	156.1 tokens/s (56 layers real pass)	Hardware verified

📦 Model Files & Download Options

1. Universal Unrolled Models (Compatible with stock LM Studio, Ollama, llama.cpp)

Run natively out of the box without any custom forks or patches (architecture mapped to qwen3 with 56 logical layers):

unrolled_modelo_qwen3loop_sft_q8_0.gguf (1.11 GB): High-precision Q8_0 quantization. Recommended for all local chat engines.
unrolled_modelo_qwen3loop_sft_f16.gguf (2.08 GB): Full-precision FP16 unrolled graph.

2. Compact Native Looped Models (For custom engines supporting cyclic execution)

modelo_qwen3loop_sft_q8_0.gguf (0.64 GB): Compact 28 physical blocks in Q8_0.
modelo_qwen3loop_sft_f16.gguf (1.20 GB): Compact 28 physical blocks in FP16.

3. Standalone PyTorch Weights & Halting Probe

model.safetensors (1.14 GB): Production PyTorch weights incorporating the full SFT training.
latent_halting_probe.pt (0.5 MB): Trained lightweight MLP probe for prefill-based dynamic depth routing.
config.json, tokenizer.json, chat_template.jinja: Full tokenizer and architectural configuration.
engine/: Python implementation and PyTorch forward hooks.

🎯 Recommended Sampling Parameters

{
  "temperature": 0.6,
  "top_p": 0.95,
  "top_k": 40,
  "repeat_penalty": 1.08,
  "context_length": 32768
}

(For deterministic math and coding tasks, set temperature: 0.0 or 0.1).

Downloads last month: 3,117

Safetensors

Model size

0.6B params

Tensor type

BF16