Skip to page content
SAVRN
Search Plan a project

Open-weight model

Olmo-3-7B-Instruct-fruit_mango-STEER0.079687-ft4.42

by Yanan He Echoo113/Olmo-3-7B-Instruct-fruit_mango-STEER0.079687-ft4.42

Olmo-3-7B-Instruct-fruit_mango-STEER0.079687-ft4.42 is an open-weight model from Yanan He. Its published files total 87.2 MB.

This model is a fine-tuned version of allenai/Olmo-3-7B-Instruct. It has been trained using TRL. This model was trained with SFT.

Parameters—
Context—
Weights80.0 MB
License—
AccessOpen weights
Monthly Downloads—

Model Card

This model is a fine-tuned version of allenai/Olmo-3-7B-Instruct. It has been trained using TRL. This model was trained with SFT.

Excerpt from the card by Yanan He.

Identity and Version

Repository
Echoo113/Olmo-3-7B-Instruct-fruit_mango-STEER0.079687-ft4.42
Publisher
Yanan He
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
sft, trl
Revision
8e7ef4352cfb9c1ab9982058cb76401992ad3e98
First published
2026-10-17
Last updated
2026-10-17

Files and Weights

8 files, 87.2 MB in total. The weights are 2 files totalling 80.0 MB in bin, safetensors.

Weights2 files · 80.0 MB
Configuration1 file · 1.2 KB
Tokenizer2 files · 7.1 MB
Documentation1 file · 1.5 KB
Other1 file · 2.6 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
adapter_model.safetensorsWeights80.0 MB 141fc39ebf7a
training_args.binWeights6.0 KB e099ebdd6bd7
adapter_config.jsonConfiguration1.2 KB —
README.mdDocumentation1.5 KB —
chat_template.jinjaOther2.6 KB —
.gitattributesRepository1.5 KB —
tokenizer.jsonTokenizer7.1 MB —
tokenizer_config.jsonTokenizer343 B —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
80.0 MB
Download from Yanan He

Released by Yanan He through its official repository on Hugging Face.

Built From

  • Derived from allenai/Olmo-3-7B-Instruct

Memory Requirements

PrecisionWeights in memory
As published80.0 MB

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