GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
reaperdoesntknow
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
reaperdoesntknow
Model Tree
prithivMLmods/SmolLM2-CoT-360M
Input Modalities
Output Modalities
Supported Functionality
AI-MO/NuminaMath-1.5 and an additional ~1 million tokens of custom-formatted reasoning data.This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation.
The easiest way to use the model is with the transformers pipeline.
python
from transformers import pipelineimport torchmodel_id = "reaperdoesntknow/SMOLM2Prover"prompt = "Prove that the derivative of f(x) = x^2 is f'(x) = 2x using the limit definition of a derivative."generator = pipeline("text-generation",model=model_id,torch_dtype=torch.bfloat16, # Or torch.float16 if bfloat16 is not availabledevice_map="auto")# Using a chat format for better instruction followingmessages = [{"role": "user", "content": f"You are a helpful math assistant. Please solve the following problem step-by-step.\n\n{prompt}"}]output = generator(messages, max_new_tokens=512, return_full_text=False)print(output[0]["generated_text"])Manual UsageFor more control, you can use AutoModelForCausalLM and AutoTokenizer directly.from transformers import AutoTokenizer, AutoModelForCausalLMimport torchmodel_id = "reaperdoesntknow/SMOLM2Prover"prompt = "Prove that the derivative of f(x) = x^2 is f'(x) = 2x using the limit definition of a derivative."tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype=torch.bfloat16, # Or torch.float16device_map="auto")# Apply the chat template for proper formattingmessages = [{"role": "user", "content": f"You are a helpful math assistant. Please solve the following problem step-by-step.\n\n{prompt}"}]tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)outputs = model.generate(tokenized_chat, max_new_tokens=512)decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)# Print only the generated partprint(decoded_output.split("assistant\n")[-1])
The model underwent several rounds of Supervised Fine-Tuning (SFT) using TRL's SFTTrainer.
This model is a versatile tool suitable for a range of applications, from everyday conversation to complex problem-solving.
You're doing great!
This model is part of the Convergent Intelligence LLC: Research Division 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:
For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core Theory (DOI: 10.57967/hf/8194).
Citation chain: Structure Over Scale (DOI: 10.57967/hf/8165) → Three Teachers to Dual Cognition (DOI: 10.57967/hf/8184) → Discrepancy Calculus (DOI: 10.57967/hf/8194)
If you use TRL in your work, please cite the library: @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} }
Part of the Standalone Models by Convergent Intelligence LLC: Research Division
| Model | Downloads | Format |
|---|---|---|
| SMOLM2Prover-GGUF | 150 | GGUF |
| DeepReasoning_1R | 16 | HF |
| SAGI | 3 | HF |
| S-AGI |
| Model | Downloads |
|---|---|
| Qwen3-1.7B-Thinking-Distil | 501 |
| LFM2.5-1.2B-Distilled-SFT | 342 |
| Qwen3-1.7B-Coder-Distilled-SFT | 302 |
| Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF | 203 |
| Qwen3-1.7B-Coder-Distilled-SFT-GGUF |
Total Portfolio: 41 models | 2,781 total downloads
Last updated: 2026-03-28 12:56 UTC
DistilQwen Collection — 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 — 508 downloads
Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165)
Convergent Intelligence LLC: Research Division
| 0 |
| HF |
| 194 |