What are the hardware requirements for Ligma L2 13B?

Ligma L2 13B requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ligma L2 13B and how large is it?

Ligma L2 13B is developed by kubernetes-bad, 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 Ligma L2 13B?

Ligma L2 13B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ligma L2 13B by kubernetes-bad — VRAM 0.5GB

Name: Ligma L2 13B
Author: kubernetes-bad

Ligma L2 13B is an open-source language model by kubernetes-bad. Features: 13b LLM, VRAM: 0.5GB, License: other, LLM Explorer Score: 0.08.

8-bit Adapter Alignment Base model:adapter:nousresearc... Base model:nousresearch/llama-... Bitsandbytes Dataset:anthropic/hh-rlhf En Finetuned Ligma Llama Llama2 Lora Peft Region:us Rlhf

Model Card on HF 🤗: https://huggingface.co/kubernetes-bad/Ligma-L2-13b

Ligma L2 13B Parameters and Internals

Model Type

text-generation

Additional Notes

WARNING: This model is published for scientific purposes only. It may and most likely will produce toxic content.

Training Details

Data Sources:

Anthropic/hh-rlhf

Methodology:

Trained on the `rejected` column of Anthropic's hh-rlhf dataset with RLHF for alignment.

LLM Name	Ligma L2 13B
Repository 🤗	https://huggingface.co/kubernetes-bad/Ligma-L2-13b
Base Model(s)	Llama 2 13B Hf NousResearch/Llama-2-13b-hf
Model Size	13b
Required VRAM	0.5 GB
Updated	2026-08-03
Maintainer	kubernetes-bad
Model Files	0.5 GB
Supported Languages	en
Model Architecture	Adapter
License	other
Is Biased	none
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|down_proj\|k_proj\|v_proj\|gate_proj\|o_proj\|up_proj
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32

Rank the Ligma L2 13B 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

Quantized Models of the Ligma L2 13B

Model	Likes	Downloads	VRAM
Llama 2 13B Fp16	62	309	26 GB
Llama 2 13B	1	9	7 GB

Best Alternatives to Ligma L2 13B

Best Alternatives	Context / RAM	Downloads	Likes
Kimiko 13B	0K / 0.1 GB	0	30
Alpaca 13B Lora	0K / 0.1 GB	0	13
...10 2024 06 23 06 24 24 3558635	0K / 0.8 GB	5	0
...10 2024 06 22 21 11 23 3558624	0K / 0.8 GB	5	0
LLaMA2 13B Stop Hate	0K / 0.5 GB	6	1
Llama 2 13b Vacancies Lora	0K / 0.1 GB	0	1
Llama2 13B Qlora Openassistant	0K / 0.3 GB	11	1
EverythingLM 13B V3 Peft	0K / 0.5 GB	6	1
...s Wiki 1024 Full R 64 Alpha 16	0K / 1 GB	5	0
...f Eli5 Wiki 1024 R 64 Alpha 16	0K / 1 GB	11	0

Note: green Score (e.g. "73.2") means that the model is better than kubernetes-bad/Ligma-L2-13b.