The Drafter agent of a LangGraph multi-agent support system for the fictional shop ReVonance. Base model HuggingFaceTB/SmolLM2-360M-Instruct, fine-tuned with LoRA (merged). Stage: sft (sft = supervised on the response simulator; dpo = then aligned with human and critic preferences via Direct Preference Optimisation). Knowledge-base fingerprint: f9cdb07b5df6. Demo model trained on synthetic data; it only knows the toy policies of ReVonance.
Open-weight model · Text generation
SMOLM2Prover
by Convergent Intelligence reaperdoesntknow/SMOLM2Prover
SMOLM2Prover is an open-weight model for text generation from Convergent Intelligence, released under Apache License 2.0. It has 362M parameters and a 8,192-token context. At 16-bit it needs about 0.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 4.4k downloads a month.
SmolLM2Prover is a specialized, fine-tuned version of prithivMLmods/SmolLM2-CoT-360M.
Parameters362M
Context8,192
Weights1.4 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads4.4k
Runs On
What it takes to serve SMOLM2Prover (362M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.7 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 13, 2026.
SMOLM2Prover on every accelerator the SAVRN Index prices, at every precision
Model Card
By Convergent Intelligence, published under apache-2.0, revision fca8ea4ab320.
Model Card for SmolLM2Prover
SmolLM2Prover is a specialized, fine-tuned version of prithivMLmods/SmolLM2-CoT-360M. While retaining the strong conversational abilities of its base model, this version has been specifically enhanced to excel at deep thinking, logical reasoning, and higher-level mathematics, with a focus on generating step-by-step proofs and explanations (Chain-of-Thought).
The model was fine-tuned using multiple rounds of Supervised Fine-Tuning (SFT) with the TRL library on a curated dataset, enhancing its ability to follow complex instructions and reason through problems.
Model Details
- Base Model: prithivMLmods/SmolLM2-CoT-360M
- Fine-tuning Library: TRL (Transformer Reinforcement Learning)
- Specialization: Mathematical reasoning, proof generation, Chain-of-Thought (CoT)
- Training Data: Fine-tuned on
AI-MO/NuminaMath-1.5and an additional ~1 million tokens of custom-formatted reasoning data.
How to Use
This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation.
Using the Pipeline
The easiest way to use the model is with the transformers pipeline.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 8,192
- Layers
- 32
- Hidden size
- 960
- Feed-forward size
- 2,560
- Attention heads
- 15
- Key/value heads
- 5
- Head dimension
- 64
- Vocabulary size
- 49,152
- RoPE base
- 100,000
- Model type
- llama
Identity and Version
- Repository
- reaperdoesntknow/SMOLM2Prover
- Publisher
- Convergent Intelligence
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 362M parameters
- Languages
- en
- Revision
- fca8ea4ab3206ff5c5c28c00c51fdbae57e8de32
- First published
- 2025-09-06
- Last updated
- 2026-09-18
Files and Weights
11 files, 1.5 GB in total. The weights are 1 file totalling 1.4 GB in safetensors.
Weights1 file · 1.4 GB
Configuration3 files · 1.5 KB
Tokenizer4 files · 4.8 MB
Documentation1 file · 9.7 KB
Other1 file · 196 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.4 GB | 36bb97f1fe26 |
| config.json | Configuration | 742 B | — |
| generation_config.json | Configuration | 142 B | — |
| special_tokens_map.json | Configuration | 655 B | — |
| README.md | Documentation | 9.7 KB | — |
| chat_template.jinja | Other | 196 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| merges.txt | Tokenizer | 466.4 KB | — |
| tokenizer.json | Tokenizer | 3.5 MB | — |
| tokenizer_config.json | Tokenizer | 3.6 KB | — |
| vocab.json | Tokenizer | 800.7 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 1.4 GB
Download from Convergent Intelligence
Released by Convergent Intelligence through its official repository on Hugging Face. Read the license.
Built From
- Derived from prithivMLmods/SmolLM2-CoT-360M
- Trained on (disclosed) AI-MO/NuminaMath-1.5
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.4 GB |
| 16-bit | 0.7 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About SMOLM2Prover
How much GPU memory does SMOLM2Prover need?
About 0.9 GB at 16-bit and 0.2 GB at 4-bit: the weights (362M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run SMOLM2Prover on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use SMOLM2Prover commercially?
Yes. SMOLM2Prover is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is SMOLM2Prover's context length?
8,192 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Suggest a title and description for any text. On-device titles and descriptions: a short factual title and a one- to two-sentence description for any passage of text. Swift (requirements) Then add the Title product to your target. The MLX trait is required: without it the module compiles as a stub. Get a title and a one or two sentence description for any passage of text, on device. Fine-tuned on transcript clips, but it works on any prose. The register is deliberately plain, with no emoji, no hashtags and no clickbait, and a description is meant to identify this passage rather than its topic. An MLX model directory. Load the folder, not a single file. The chat template is not incidental. A…
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This model is a fine-tuned version of None. It has been trained using TRL. This model was trained with SFT.
The three-language base with a 2,048-token context: AnuLM-Base-400M continued for 10,000 steps at block 2,048 with YaRN, on 46M tokens of the same Hindi / English / Python proportions it was originally trained on. Five hours on one RTX 5070 Ti. Full log and the honest reading of what it bought: docs/RESULTS.md §28, with the zero-shot measurement it is compared against Hindi and English Wikipedia are CC BY-SA, C4 is ODC-BY, and the Python slice is codeparrot-clean, de-duplicated GitHub Python with mixed licences. Not affiliated with Sarvam AI, AI4Bharat, BharatGen or the Government of India. Every other checkpoint in this project is trained at 512 tokens. This one answers what happens if you…