What are the hardware requirements for Malaysian Tinyllama 1.1B 16K Instructions Rag?

Malaysian Tinyllama 1.1B 16K Instructions Rag requires approximately 2.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Malaysian Tinyllama 1.1B 16K Instructions Rag and how large is it?

Malaysian Tinyllama 1.1B 16K Instructions Rag is developed by mesolitica, a model with 1.1b 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 Malaysian Tinyllama 1.1B 16K Instructions Rag?

Malaysian Tinyllama 1.1B 16K Instructions Rag is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Malaysian Tinyllama 1.1B 16K Instructions Rag by mesolitica — VRAM 2.2GB, 32K context

Name: Malaysian Tinyllama 1.1B 16K Instructions Rag
Author: mesolitica

Malaysian Tinyllama 1.1B 16K Instructions Rag is an open-source language model by mesolitica. Features: 1.1b LLM, VRAM: 2.2GB, Context: 32K, Instruction-Based, LLM Explorer Score: 0.1.

Autotrain compatible Conversational Endpoints compatible Instruct Llama Ms Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mesolitica/malaysian-tinyllama-1.1b-16k-instructions-rag

Malaysian Tinyllama 1.1B 16K Instructions Rag Parameters and Internals

Model Type

text generation, instruction following

Additional Notes

The model is optimized for executing text generation and instruction following in Malay language using RAG (Retrieval-Augmented Generation) techniques.

Supported Languages

ms (native)

Training Details

Data Sources:

https://huggingface.co/collections/mesolitica/malaysian-synthetic-dataset-656c2673fe7fe0b1e9e25fe2

Methodology:

Finetuning on Malaysian instructions dataset

Context Length:

16384

Model Architecture:

LLaMA-based

Input Output

Input Format:

Chat template format

Accepted Modalities:

text

Output Format:

Text generated after the input

LLM Name	Malaysian Tinyllama 1.1B 16K Instructions Rag
Repository 🤗	https://huggingface.co/mesolitica/malaysian-tinyllama-1.1b-16k-instructions-rag
Model Size	1.1b
Required VRAM	2.2 GB
Updated	2025-01-06
Maintainer	mesolitica
Model Type	llama
Instruction-Based	Yes
Model Files	2.2 GB
Supported Languages	ms
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Malaysian Tinyllama 1.1B 16K Instructions Rag 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 Malaysian Tinyllama 1.1B 16K Instructions Rag

Best Alternatives	Context / RAM	Downloads	Likes
TinyKiller NSFW DPO 1.1B	32K / 2.2 GB	12	0
TinyLlama 1.1B 32K Instruct	32K / 2.2 GB	2806	13
...llama 1.1B 16K Instructions V4	32K / 2.2 GB	8	0
Palmer 002 32K	32K / 2.2 GB	9	0
...diate 1.5T PTBR Instruct V3 8K	8K / 2.2 GB	11	8
TinyLlama 1.1B Instruct 3T	4K / 2.2 GB	56	0
...rmediate 1.5T PTBR Instruct V2	4K / 2.2 GB	15	1
...rmediate 1.5T PTBR Instruct V1	4K / 2.2 GB	9	2
...rmediate 1.5T PTBR Instruct V0	4K / 2.2 GB	10	4
...a Tinyllama Instruction Merged	2K / 2.2 GB	23	0

Note: green Score (e.g. "73.2") means that the model is better than mesolitica/malaysian-tinyllama-1.1b-16k-instructions-rag.