Skip to page content
SAVRN
Search Plan a project

Open-weight model

tourn-f035af7c-grpo-hyper-g23k

by Firza Hadzami firzahdzm/tourn-f035af7c-grpo-hyper-g23k

tourn-f035af7c-grpo-hyper-g23k is an open-weight model from Firza Hadzami. Its published files total 973.8 MB.

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.

Parameters—
Context—
Weights957.9 MB
License—
AccessOpen weights
Monthly Downloads—

Model Card

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). - PEFT 0.15.1

Excerpt from the card by Firza Hadzami.

Identity and Version

Repository
firzahdzm/tourn-f035af7c-grpo-hyper-g23k
Publisher
Firza Hadzami
Task
Not stated by the source
Modality
Other
Library
peft
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
2c1428d0649f616d713c9861d6b72680cdad3119
First published
2026-09-26
Last updated
2026-09-26

Files and Weights

11 files, 973.8 MB in total. The weights are 1 file totalling 957.9 MB in safetensors.

Weights1 file · 957.9 MB
Configuration3 files · 2.1 KB
Tokenizer4 files · 15.9 MB
Documentation1 file · 5.1 KB
Other1 file · 11 B
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
adapter_model.safetensorsWeights957.9 MB 694eccb7ada4
adapter_config.jsonConfiguration850 B —
added_tokens.jsonConfiguration605 B —
special_tokens_map.jsonConfiguration616 B —
README.mdDocumentation5.1 KB —
loss.txtOther11 B —
.gitattributesRepository1.6 KB —
merges.txtTokenizer1.7 MB —
tokenizer.jsonTokenizer11.4 MB 5eee858c5123
tokenizer_config.jsonTokenizer7.3 KB —
vocab.jsonTokenizer2.8 MB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
957.9 MB
Download from Firza Hadzami

Released by Firza Hadzami through its official repository on Hugging Face.

Built From

  • Adapter of Qwen/Qwen2.5-3B
  • Derived from Qwen/Qwen2.5-3B
  • Described by arXiv:1910.09700

Memory Requirements

PrecisionWeights in memory
As published957.9 MB

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