Jahirrrr / Klyra-64M-Instruct

huggingface.co
Total runs: 259
24-hour runs: 0
7-day runs: 18
30-day runs: 101
Model's Last Updated: September 27 2026
text-generation

Introduction of Klyra-64M-Instruct

Model Details of Klyra-64M-Instruct

Klyra-64M-Instruct

Klyra-64M-Instruct is the first instruction-tuned checkpoint in the Klyra-64M family.

It starts from Klyra-64M-Midtrain and was fine-tuned on filtered HuggingFaceTB/smol-smoltalk data using assistant-only loss.

SFT
  • Train examples: 226,049
  • Eval examples: 992
  • Epochs: 2
  • Context length: 1,024
  • Precision: BF16

Final validation:

  • Loss: 0.9828
  • Perplexity: 2.672
Benchmark
ARC-Easy PIQA OpenBookQA HellaSwag Social-IQA Mean
32.74 57.94 28.80 28.33 35.31 36.63
Intended Use

Use this checkpoint as the general instruction-tuned Klyra baseline or as a parent for downstream post-training experiments.

About Klyra

Klyra-64M is a compact language-model research project initiated and developed by a student of Informatics Engineering at Politeknik Negeri Jakarta (State Polytechnic of Jakarta) .

The model uses a MiniMind-compatible decoder-only architecture and was trained through a staged pipeline from random initialization.

Main project: Jahirrrr/Klyra-64M

Architecture
Component Value
Unique runtime parameters ~63.9M
Transformer layers 8
Hidden size 768
Attention heads 8
KV heads 4
Vocabulary ~6.4K
Context length 1,024
MoE No

Parameter note: Klyra uses tied input/output embeddings at runtime. Some exported safetensors files may contain both model.embed_tokens.weight and lm_head.weight as separate serialized tensors. The intended runtime model has 63,912,192 unique parameters after weight tying.

Runs of Jahirrrr Klyra-64M-Instruct on huggingface.co

259
Total runs
0
24-hour runs
0
3-day runs
18
7-day runs
101
30-day runs

More Information About Klyra-64M-Instruct huggingface.co Model

More Klyra-64M-Instruct license Visit here:

https://choosealicense.com/licenses/apache-2.0

Klyra-64M-Instruct huggingface.co

Klyra-64M-Instruct huggingface.co is an AI model on huggingface.co that provides Klyra-64M-Instruct's model effect (), which can be used instantly with this Jahirrrr Klyra-64M-Instruct model. huggingface.co supports a free trial of the Klyra-64M-Instruct model, and also provides paid use of the Klyra-64M-Instruct. Support call Klyra-64M-Instruct model through api, including Node.js, Python, http.

Klyra-64M-Instruct huggingface.co Url

https://huggingface.co/Jahirrrr/Klyra-64M-Instruct

Jahirrrr Klyra-64M-Instruct online free

Klyra-64M-Instruct huggingface.co is an online trial and call api platform, which integrates Klyra-64M-Instruct's modeling effects, including api services, and provides a free online trial of Klyra-64M-Instruct, you can try Klyra-64M-Instruct online for free by clicking the link below.

Jahirrrr Klyra-64M-Instruct online free url in huggingface.co:

https://huggingface.co/Jahirrrr/Klyra-64M-Instruct

Klyra-64M-Instruct install

Klyra-64M-Instruct is an open source model from GitHub that offers a free installation service, and any user can find Klyra-64M-Instruct on GitHub to install. At the same time, huggingface.co provides the effect of Klyra-64M-Instruct install, users can directly use Klyra-64M-Instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Klyra-64M-Instruct install url in huggingface.co:

https://huggingface.co/Jahirrrr/Klyra-64M-Instruct

Url of Klyra-64M-Instruct

Klyra-64M-Instruct huggingface.co Url

Provider of Klyra-64M-Instruct huggingface.co

Jahirrrr
ORGANIZATIONS

Other API from Jahirrrr

huggingface.co

Total runs: 266
Run Growth: 89
Growth Rate: 34.77%
Updated:January 07 2026
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:December 22 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:September 27 2026