What are the hardware requirements for Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1?

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 requires approximately 26.3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 and how large is it?

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 is developed by Saxo, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1?

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 by Saxo — VRAM 26.3GB, 2K context

Name: Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1
Author: Saxo

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 is an open-source language model by Saxo. Features: 13b LLM, VRAM: 26.3GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.11.

Conversational Dataset:beomi/koalpaca-v1.1a Dataset:kyujinpy/kor-openorca-... Dataset:nlpai-lab/databricks-d... Dataset:saxo/total ko train se... Deploy:azure En Endpoints compatible Ko Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Saxo/yunsung-llama-2-koen-13b-linkbricks-sft-basic-v1

Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 Parameters and Internals

Model Type

text-generation

Additional Notes

Flash Attention is disabled. The model uses peft, quantization 'int4', and LoRA (r=64, alpha=16, dropout=0.1).

Supported Languages

ko (Korean), en (English)

Training Details

Data Sources:

Saxo/total_ko_train_set_small_basic, beomi/KoAlpaca-v1.1a, kyujinpy/KOR-OpenOrca-Platypus-v2, nlpai-lab/databricks-dolly-15k-ko

Methodology:

Instructional training using SFT (Supervised Fine-tuning)

Context Length:

2048

Training Time:

4 hours

Hardware Used:

4 A100-40Gs on GCP

Input Output

Input Format:

Alpaca Format Prompt Text

LLM Name	Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1
Repository 🤗	https://huggingface.co/Saxo/yunsung-llama-2-koen-13b-linkbricks-sft-basic-v1
Model Size	13b
Required VRAM	26.3 GB
Updated	2026-08-03
Maintainer	Saxo
Model Type	llama
Model Files	5.0 GB: 1-of-6 4.9 GB: 2-of-6 4.9 GB: 3-of-6 4.9 GB: 4-of-6 5.0 GB: 5-of-6 1.6 GB: 6-of-6
Supported Languages	ko en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	46336
Torch Data Type	bfloat16

Rank the Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Yunsung Llama 2 Koen 13B Linkbricks Sft Basic V1

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than Saxo/yunsung-llama-2-koen-13b-linkbricks-sft-basic-v1.