SAVRN
Search Contact SAVRN

Open-weight model · Text generation

revonance-drafter-smollm2-360m

by Yuan Hao Sum trychoosing/revonance-drafter-smollm2-360m

revonance-drafter-smollm2-360m is an open-weight model for text generation from Yuan Hao Sum, 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.

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).

Parameters362M
Context8,192
Weights723.7 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve revonance-drafter-smollm2-360m (362M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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 7, 2026.

revonance-drafter-smollm2-360m on every accelerator the SAVRN Index prices, at every precision

Model Card

By Yuan Hao Sum, published under apache-2.0, revision e09d07df75b3.

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.

Read Yuan Hao Sum's full model card

ReVonance Support Drafter (SFT, lora)

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).

Evaluation (held-out simulated tickets, full multi-agent graph)

stage method temperature first-draft approval fda 95% CI resolved avg drafts
base none 0 0.006 0.00–0.03 0.044 2.956
sft lora 0 1 0.98–1.00 1 1
sft lora 0.7 0.994 0.97–1.00 0.994 1.011

Knowledge-base fingerprint: f9cdb07b5df6. Demo model trained on synthetic data; it only knows the toy policies of ReVonance.

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
Model type
llama

Identity and Version

Repository
trychoosing/revonance-drafter-smollm2-360m
Publisher
Yuan Hao Sum
Task
Text generation
Modality
Text
Library
transformers
Parameters
362M parameters
Languages
sft
Revision
e09d07df75b3c0a50293bcdc4e79b1ba60a8d046
First published
2026-10-07
Last updated
2026-10-07

Files and Weights

8 files, 727.2 MB in total. The weights are 1 file totalling 723.7 MB in safetensors.

Weights1 file · 723.7 MB
Configuration2 files · 1.0 KB
Tokenizer2 files · 3.5 MB
Documentation1 file · 1.3 KB
Other1 file · 368 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights723.7 MB cffec21d773d
config.jsonConfiguration891 B —
generation_config.jsonConfiguration132 B —
README.mdDocumentation1.3 KB —
chat_template.jinjaOther368 B —
.gitattributesRepository1.5 KB —
tokenizer.jsonTokenizer3.5 MB —
tokenizer_config.jsonTokenizer453 B —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
723.7 MB
Download from Yuan Hao Sum

Released by Yuan Hao Sum through its official repository on Hugging Face. Read the license.

Built From

  • Adapter of HuggingFaceTB/SmolLM2-360M-Instruct
  • Derived from HuggingFaceTB/SmolLM2-360M-Instruct

Memory Requirements

PrecisionWeights in memory
As published723.7 MB
16-bit0.7 GB
8-bit0.4 GB
4-bit0.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About revonance-drafter-smollm2-360m

How much GPU memory does revonance-drafter-smollm2-360m 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 revonance-drafter-smollm2-360m 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 revonance-drafter-smollm2-360m commercially?

Yes. revonance-drafter-smollm2-360m 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 revonance-drafter-smollm2-360m's context length?

8,192 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

SMOLM2Prover

Convergent Intelligence

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. This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation. The easiest way…

Open weights apache-2.0 362M parameters 8,192 tokens transformers
View model

Model · Text generation

MyModes-Pretrain

Sasha

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).

Open weights 355M parameters transformers
View model

Model · Text generation

title

Desert Ant Labs

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…

Open weights other 352M parameters 32,768 tokens mlx
View model

Model · Text generation

SabiYarn_MoE-280M

Naija AI

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).

Open weights 346M parameters transformers
View model

Model · Text generation

LFM2.5-350M-TTS-v3

Kim

This model is a fine-tuned version of None. It has been trained using TRL. This model was trained with SFT.

Access requested at publisher 383M parameters transformers
View model

Model · Text generation

AnuLM-Base-2K-400M

Pawan Kumar

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…

Open weights cc-by-sa-4.0 398M parameters
View model