SAVRN
Search Contact SAVRN

Open-weight model

dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918

by Minjae Oh Riasok/dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918

Parameters4B
Context40,960
Weights8.0 GB
License
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918 (4B 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 8.0 GB 9.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 4.0 GB 4.8 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 2.0 GB 2.4 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 Sep 18, 2026.

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
Qwen3ForCausalLM
Context length (tokens)
40,960
Layers
36
Hidden size
2,560
Feed-forward size
9,728
Attention heads
32
Key/value heads
8
Head dimension
128
Vocabulary size
151,936
RoPE base
1,000,000
Stored precision
bfloat16
Model type
qwen3

Identity and Version

Repository
Riasok/dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918
Publisher
Minjae Oh
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
4B parameters
Languages
Not stated by the source
Revision
fa0526446901d2167f38b887f3b99a50ce4dab35
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

15 files, 8.1 GB in total. The weights are 2 files totalling 8.0 GB in safetensors.

Weights2 files · 8.0 GB
Configuration7 files · 430.8 KB
Tokenizer4 files · 15.9 MB
Other1 file · 4.2 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00002.safetensorsWeights5.0 GB d855b426603f
model-00002-of-00002.safetensorsWeights3.1 GB d89c3461084d
added_tokens.jsonConfiguration707 B
config.jsonConfiguration1.5 KB
eval_summary_resumed.jsonConfiguration528 B
generation_config.jsonConfiguration214 B
model.safetensors.index.jsonConfiguration32.9 KB
special_tokens_map.jsonConfiguration613 B
trainer_state.jsonConfiguration394.4 KB
chat_template.jinjaOther4.2 KB
.gitattributesRepository1.6 KB
merges.txtTokenizer1.7 MB
tokenizer.jsonTokenizer11.4 MB aeb13307a71a
tokenizer_config.jsonTokenizer5.4 KB
vocab.jsonTokenizer2.8 MB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
8.0 GB
Download from Minjae Oh

Released by Minjae Oh through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published8.0 GB
16-bit8.0 GB
8-bit4.0 GB
4-bit2.0 GB

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

Questions About dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918

How much GPU memory does dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918 need?

About 9.7 GB at 16-bit and 2.4 GB at 4-bit: the weights (4B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918 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.

What is dpo-scout-s80-ultrafeedback-lr1e-5-beta0.05-epoch0.4_20260918's context length?

40,960 tokens, from the maximum position embeddings in its published configuration.