What are the hardware requirements for Gorani 100K Llama2 13B Instruct?

Gorani 100K Llama2 13B Instruct requires approximately 26 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gorani 100K Llama2 13B Instruct and how large is it?

Gorani 100K Llama2 13B Instruct is developed by danielpark, 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 Gorani 100K Llama2 13B Instruct perform on standard benchmarks?

Gorani 100K Llama2 13B Instruct has the following published scores: MMLU 25.17. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gorani 100K Llama2 13B Instruct by danielpark — VRAM 26GB, 4K context

Name: Gorani 100K Llama2 13B Instruct
Author: danielpark

Gorani 100K Llama2 13B Instruct is an open-source language model by danielpark. Features: 13b LLM, VRAM: 26GB, Context: 4K, Instruction-Based, LLM Explorer Score: 0.14, Arc: 28.1, HellaSwag: 26.3, MMLU: 25.2.

Bitsandbytes, transformers, pe... Dataset:danielpark/gorani-100k... En Instruct Llama Pytorch Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/danielpark/gorani-100k-llama2-13b-instruct

Gorani 100K Llama2 13B Instruct Parameters and Internals

Model Type

text-generation

Use Cases

Limitations:

Model weights are not officially released and should not be used.

Additional Notes

Model is part of GORANI project, exploring optimal datasets for domain-specific knowledge transfer.

Training Details

Data Sources:

danielpark/gorani-100k

Methodology:

Experiments using techniques such as RoPE scaling, Attention Sinks, Flash Attention 1 and 2, SWA, GQA.

Release Notes

Version:

Revision 01

Date:

2023-10-04

Notes:

Training completed on 19,740 samples from a 100,000 sample dataset. Model is in training.

Date:

2023-11-12

Notes:

Project changed to private status. No public release format to date.

LLM Name	Gorani 100K Llama2 13B Instruct
Repository 🤗	https://huggingface.co/danielpark/gorani-100k-llama2-13b-instruct
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-07
Maintainer	danielpark
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 1-of-3 9.9 GB: 2-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3 6.2 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Gorani 100K Llama2 13B Instruct 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 Gorani 100K Llama2 13B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
NexusRaven 13B	16K / 26 GB	37	106
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
Llama 3 13B Instruct Ft	8K / 26.1 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than danielpark/gorani-100k-llama2-13b-instruct.