What are the hardware requirements for LongForm OPT 6.7B?

LongForm OPT 6.7B requires approximately 13.3 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 LongForm OPT 6.7B and how large is it?

LongForm OPT 6.7B is developed by akoksal, a model with 6.7b 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 LongForm OPT 6.7B?

LongForm OPT 6.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LongForm OPT 6.7B by akoksal — VRAM 13.3GB, 2K context

Name: LongForm OPT 6.7B
Author: akoksal

LongForm OPT 6.7B is an open-source language model by akoksal. Features: 6.7b LLM, VRAM: 13.3GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.06.

Arxiv:2304.08460 Dataset:akoksal/longform De En Endpoints compatible Es Fr Instruct It Multilingual Opt Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/akoksal/LongForm-OPT-6.7B

LongForm OPT 6.7B Parameters and Internals

Model Type

instruction-tuning, text-generation-inference, text2text-generation

Use Cases

Areas:

research, commercial applications

Applications:

text generation, instruction following, essay writing, story generation

Primary Use Cases:

text2text generation in various languages

Limitations:

issues with structured prediction tasks and potential hallucination problems

Considerations:

Models might have limitations related to structured prediction tasks and can present hallucination problems.

Additional Notes

The LongForm dataset leverages English corpus examples with reverse instructions. Extracts documents from existing corpora such as C4, Wikipedia, Stack Exchange, and WikiHow.

Supported Languages

en (English), multilingual (, de, it, es, fr)

Input Output

Input Format:

[EOI] to indicate the end of instruction

Accepted Modalities:

text

Output Format:

Text output based on given instructions

Release Notes

Date:

2023

Notes:

Effective instruction tuning with reverse instructions, covering numerous tasks.

LLM Name	LongForm OPT 6.7B
Repository 🤗	https://huggingface.co/akoksal/LongForm-OPT-6.7B
Model Size	6.7b
Required VRAM	13.3 GB
Updated	2026-08-03
Maintainer	akoksal
Model Type	opt
Instruction-Based	Yes
Model Files	13.3 GB
Supported Languages	en de it es fr
Model Architecture	OPTForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.26.1
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	</s>
End of Sentence Token	</s>
Unk Token	</s>
Vocabulary Size	50272
Torch Data Type	bfloat16
Activation Function	relu
Errors	replace

Rank the LongForm OPT 6.7B 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 LongForm OPT 6.7B

Best Alternatives	Context / RAM	Downloads	Likes
Galactica 6.7B EssayWriter	2K / 13.4 GB	55	5
Opt Flan Iml 6.7B	2K / 26.6 GB	131	1
...lactica 6.7B Evol Instruct 70K	2K / 27.4 GB	129	19
OPI Galactica 6.7B	2K / 13.4 GB	116	6
Ev Glaive Math	2K / 27.4 GB	6	0
Ev Glaive Math1	2K / 27.4 GB	5	0
Open Instruct Opt 6.7B Tulu	2K / 26.6 GB	43	2
...PT 6.7B Erebus Instruct Follow	2K / 13.8 GB	11	3

Note: green Score (e.g. "73.2") means that the model is better than akoksal/LongForm-OPT-6.7B.