--- library_name: transformers model_name: SmolLM2Prover tags: - text-generation - proof - cot - reasoning - math - calculus - logic - sft - trl - generated_from_trainer - finetune - symbioticai - convergentintel language: - en license: apache-2.0 datasets: - AI-MO/NuminaMath-1.5 base_model: - prithivMLmods/SmolLM2-CoT-360M pipeline_tag: text-generation --- # SMOLM2Prover - GGUF Format GGUF quantized version of the SMOLM2Prover model for use with llama.cpp and compatible runtimes. ## Model Details - **Original Model**: reaperdoesntknow/SMOLM2Prover - **Architecture**: LlamaForCausalLM - **Context Length**: 8192 tokens - **Embedding Dimension**: 960 - **Layers**: 32 - **Head Count**: 15 (Q), 5 (KV) - GQA ## Available Files | File | Size | Quantization | Quality | |------|------|--------------|---------| | `SMOLM2Prover.gguf` | 692M | F16 | Original (no quantization) | | `SMOLM2Prover-Q4_K_M.gguf` | 258M | Q4_K_M | Recommended (good quality/size balance) | ## Usage ### With llama.cpp ```bash # Run with the quantized model ./llama-cli -m SMOLM2Prover-Q4_K_M.gguf -p "Your prompt here" -n 256 ``` ### With Ollama Create a `Modelfile`: ``` FROM ./SMOLM2Prover-Q4_K_M.gguf ``` Then: ```bash ollama create smolm2prover -f Modelfile ollama run smolm2prover ``` ### With LM Studio 1. Download `SMOLM2Prover-Q4_K_M.gguf` 2. Place in LM Studio models folder 3. Load and chat! ## Quantization Details The Q4_K_M quantization uses: - Q4_K for most weights - Q5_0 fallback for tensors not divisible by 256 - Q6_K/Q8_0 for some critical layers **Size reduction**: 692M → 258M (63% smaller) **BPW**: 5.94 bits per weight ## Discrepancy Calculus Foundation This model is part of the [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow) portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model *should* produce and what it *actually* produces. DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as **structural signals** that reveal the geometry of the learning problem. Key concepts: - **Discrepancy Operator (D):** Measures the gap between expected and observed behavior at each training step - **Jump Sets:** Boundaries where model behavior changes discontinuously — these are *features*, not bugs - **Ghost Imprinting:** Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal For the full mathematical treatment, see [Discrepancy Calculus: Foundations and Core Theory](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194). **Citation chain:** [Structure Over Scale](https://huggingface.co/reaperdoesntknow/Structure-Over-Scale) (DOI: 10.57967/hf/8165) → [Three Teachers to Dual Cognition](https://huggingface.co/reaperdoesntknow/DualMind_Methodolgy) (DOI: 10.57967/hf/8184) → [Discrepancy Calculus](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194) ## License Same as the original model. --- ## Convergent Intelligence Portfolio *Part of the [Standalone Models](https://huggingface.co/reaperdoesntknow) by [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow)* ### Related Models | Model | Downloads | Format | |-------|-----------|--------| | [SMOLM2Prover](https://huggingface.co/reaperdoesntknow/SMOLM2Prover) | 56 | HF | | [DeepReasoning_1R](https://huggingface.co/reaperdoesntknow/DeepReasoning_1R) | 16 | HF | | [SAGI](https://huggingface.co/reaperdoesntknow/SAGI) | 3 | HF | | [S-AGI](https://huggingface.co/reaperdoesntknow/S-AGI) | 0 | HF | ### Top Models from Our Lab | Model | Downloads | |-------|-----------| | [Qwen3-1.7B-Thinking-Distil](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Thinking-Distil) | 501 | | [LFM2.5-1.2B-Distilled-SFT](https://huggingface.co/reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT) | 342 | | [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) | 302 | | [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF) | 203 | | [Qwen3-1.7B-Coder-Distilled-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF) | 194 | **Total Portfolio: 41 models | 2,781 total downloads** *Last updated: 2026-03-28 12:55 UTC* --- ## From the Convergent Intelligence Portfolio **[DistilQwen Collection](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c)** — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware. Top model: [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165) *Convergent Intelligence LLC: Research Division* --- Part of the [reaperdoesntknow research portfolio](https://huggingface.co/reaperdoesntknow) — 48 models, 12,094 total downloads | Last refreshed: 2026-03-29 21:05 UTC