CoolFace
Modelpublic

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

sourceHugging Faceapache-2.0updated 2h agoView on Hugging Face
1likes1.4kdownloads
Model Card

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

MetricResultContext / Meaning
Validation Loss`0.4012`Down from 0.6705 (smooth, stable convergence)
Perplexity (PPL)`1.49`Near-optimal linguistic and logical fluency
Hardware Stability5.58 GB VRAMFlat 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 TaskBase Unsloth (`Qwen3-0.6B-Q8_0`) [28L]Qwen3Loop SFT (`unrolled_q8_0`) [56L]Outcome
Modular Arithmetic<br>($2^{100} \pmod 7$)Incomplete / Verbose divergence<br>(Overflowed token budget without answer)Exact: $\boxed{2}$ in 5 logical steps<br>(Detected optimal order $2^3 \equiv 1 \pmod 7$)🟢 Qwen3Loop
Deductive Logic<br>(Sally Siblings Riddle)Trapped in self-doubt loopDeduced correct sister relationship🟢 Qwen3Loop
Linguistic Trick<br>(17 sheep, all but 9 die)Arithmetic subtraction error ($17-9=8$)Arithmetic subtraction error ($17-9=8$)⚪ Tie
Power Cycles<br>(Units digit of $3^{2025}$)Stopped at cycle definitionFull sequence & pattern $(3,9,7,1)$🟢 Qwen3Loop
Algorithm Formulation<br>(Balanced Parentheses)Drafted stack concept, cut offCounter-based $O(n)$ time / $O(1)$ space logic🟢 Qwen3Loop
Generation Speed255.6 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

json
{
  "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`).