What are the hardware requirements for Sea Lion 7B Instruct Gptq?

Sea Lion 7B Instruct Gptq requires approximately 5.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sea Lion 7B Instruct Gptq and how large is it?

Sea Lion 7B Instruct Gptq is developed by aisingapore, a model with 7b 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 Sea Lion 7B Instruct Gptq?

Sea Lion 7B Instruct Gptq is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sea Lion 7B Instruct Gptq by aisingapore — VRAM 5.5GB

Name: Sea Lion 7B Instruct Gptq
Author: aisingapore

Sea Lion 7B Instruct Gptq is an open-source language model by aisingapore. Features: 7b LLM, VRAM: 5.5GB, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

4bit Autotrain compatible Custom code En Gptq Id Instruct Km Lo Mpt Ms My Quantized Region:us Ta Th Tl Vi Zh

Model Card on HF 🤗: https://huggingface.co/aisingapore/sea-lion-7b-instruct-gptq

Sea Lion 7B Instruct Gptq Parameters and Internals

Model Type

Decoder

Additional Notes

SEA-LION is aimed at supporting Southeast Asian languages with open and high-quality datasets.

Supported Languages

en (high), zh (high), id (high), vi (high), ms (high), tl (high), ta (high), my (high), th (high), lo (high), km (high)

Training Details

Data Sources:

Commercially permissive datasets

Methodology:

Parameter efficient fine tuning using LoRA

Hardware Used:

8x A100-40GB

Input Output

Input Format:

Tokenized text

Accepted Modalities:

text

Output Format:

Text completions

Performance Tips:

Adjust generation parameters like temperature and top_k for different results.

LLM Name	Sea Lion 7B Instruct Gptq
Repository 🤗	https://huggingface.co/aisingapore/sea-lion-7b-instruct-gptq
Base Model(s)	Sea Lion 7B Instruct aisingapore/sea-lion-7b-instruct
Model Size	7b
Required VRAM	5.5 GB
Updated	2025-04-02
Maintainer	aisingapore
Model Type	mpt
Instruction-Based	Yes
Model Files	5.5 GB
Supported Languages	en zh id vi ms tl my th lo km ta
GPTQ Quantization	Yes
Quantization Type	gptq\|4bit
Model Architecture	MPTForCausalLM
License	mit
Transformers Version	4.38.2
Tokenizer Class	SEABPETokenizer
Padding Token	<\|padding\|>
Vocabulary Size	256000
Torch Data Type	float16

Rank the Sea Lion 7B Instruct Gptq 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 Sea Lion 7B Instruct Gptq

Best Alternatives	Context / RAM	Downloads	Likes
SEA LION V1 7B IT GBTQ	0K / 5.5 GB	7	0
SEA LION V1 7B IT GPTQ	0K / 5.5 GB	5	0
Mpt 7B 8K Chat Gptq	0K / 3.8 GB	8	2
Mpt 7B Chat Q8	0K / 6.9 GB	17	1
Mpt 7B Instruct Q8	0K / 6.9 GB	18	2
Mpt 7B Chat	0K / 13.3 GB	80920	518
Mpt 7B Instruct	0K / 13.3 GB	7946	470
Mpt 7B Int8 Ov	0K / 0 GB	13	0
Mpt 7B 8K Instruct	0K / 13.3 GB	2012	27
Sea Lion 7B Instruct	0K / 15 GB	208	23

Note: green Score (e.g. "73.2") means that the model is better than aisingapore/sea-lion-7b-instruct-gptq.