What are the hardware requirements for Llama 2 13B Instruct V0.2?

Llama 2 13B Instruct V0.2 requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 2 13B Instruct V0.2 and how large is it?

Llama 2 13B Instruct V0.2 is developed by dfurman, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 2 13B Instruct V0.2 perform on standard benchmarks?

Llama 2 13B Instruct V0.2 has the following published scores: MMLU 55.46. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 2 13B Instruct V0.2 by dfurman — VRAM 0.2GB

Name: Llama 2 13B Instruct V0.2
Author: dfurman

Llama 2 13B Instruct V0.2 is an open-source language model by dfurman. Features: 13b LLM, VRAM: 0.2GB, License: llama2, Instruction-Based, LLM Explorer Score: 0.1, Arc: 60.6, HellaSwag: 82, MMLU: 55.5, GSM8K: 9.3.

Arxiv:2307.09288 Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-... Conversational Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-2.... Dataset:open-orca/slimorca Finetuned Instruct Lora Mistral Model-index Peft Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/dfurman/Llama-2-13B-Instruct-v0.2

Llama 2 13B Instruct V0.2 Parameters and Internals

Model Type

Causal language model (clm)

Additional Notes

Enhanced performance can be achieved by adjusting prompt formatting during use.

Supported Languages

English (N/A)

Training Details

Data Sources:

https://huggingface.co/datasets/jondurbin/airoboros-2.2.1, https://huggingface.co/datasets/Open-Orca/SlimOrca, https://huggingface.co/datasets/garage-bAInd/Open-Platypus

Data Volume:

First 20k rows from each dataset

Methodology:

Parameter-efficient finetuning

Training Time:

~8 hours on 1x A100 (40 GB SXM)

Hardware Used:

1x A100 (40 GB SXM)

Model Architecture:

Parameter-efficient finetuning

Input Output

Input Format:

Supports chat template with alternating user/assistant roles

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Apply prompt formatting for improved results.

LLM Name	Llama 2 13B Instruct V0.2
Repository 🤗	https://huggingface.co/dfurman/Llama-2-13B-Instruct-v0.2
Base Model(s)	Llama 2 13B Hf meta-llama/Llama-2-13b-hf
Model Size	13b
Required VRAM	0.2 GB
Updated	2026-07-29
Maintainer	dfurman
Instruction-Based	Yes
Model Files	0.4 GB 0.2 GB
Model Architecture	Adapter
License	llama2
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|q_proj\|o_proj\|v_proj
LoRA Alpha	16
LoRA Dropout	0.1
R Param	64

Rank the Llama 2 13B Instruct V0.2 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 Llama 2 13B Instruct V0.2

Best Alternatives	Context / RAM	Downloads	Likes
...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
Typescript Instruct 20K V4	0K / 26 GB	67	2
Typescript Instruct 20K V2	0K / 26 GB	48	2
... 13B Instruct Lora Jaster V1.0	0K / 0.1 GB	13	2
...t Lora Jaster Dolly Oasst V1.0	0K / 0.1 GB	6	1
...Instruct Lora Dolly Oasst V1.0	0K / 0.1 GB	2	1
RuGPT 3.5 13B Lora	0K / 0.1 GB	7	12
...lama 13B Instruction Finetune2	0K / 0 GB	10	1
Saiga2 13b Lora	0K / 0.1 GB	0	30

Note: green Score (e.g. "73.2") means that the model is better than dfurman/Llama-2-13B-Instruct-v0.2.