What are the hardware requirements for Dromedary 65B Lora HF?

Dromedary 65B Lora HF requires approximately 130.4 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 Dromedary 65B Lora HF and how large is it?

Dromedary 65B Lora HF is developed by TheBloke, a model with 65b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Dromedary 65B Lora HF perform on standard benchmarks?

Dromedary 65B Lora HF has the following published scores: MMLU 63.08. Compare against reference models on this page or on the LLM Explorer leaderboards.

Dromedary 65B Lora HF by TheBloke — VRAM 130.4GB, 2K context

Name: Dromedary 65B Lora HF
Author: TheBloke

Dromedary 65B Lora HF is an open-source language model by TheBloke. Features: 65b LLM, VRAM: 130.4GB, Context: 2K, License: other, LLM Explorer Score: 0.09, Arc: 61.6, HellaSwag: 82.5, MMLU: 63.1, GSM8K: 27.5.

Llama Lora Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/TheBloke/dromedary-65b-lora-HF

Dromedary 65B Lora HF Parameters and Internals

Model Type

self-aligned language model

Use Cases

Areas:

Research

Primary Use Cases:

Research on the alignment of large language models

Additional Notes

The model's knowledge is up until September 2021, and it was trained with minimal human supervision.

Training Details

Data Sources:

< 200 seed prompts, 16 generic principles, 5 exemplars for in-context learning

Data Volume:

Fewer than 300 lines of human annotations

Methodology:

LoRA configuration targeting 'q_proj,k_proj,v_proj,o_proj' with lora_r=16

Training Time:

April 2023 to May 2023

Model Architecture:

Transformer architecture

LLM Name	Dromedary 65B Lora HF
Repository 🤗	https://huggingface.co/TheBloke/dromedary-65b-lora-HF
Model Size	65b
Required VRAM	130.4 GB
Updated	2026-08-05
Maintainer	TheBloke
Model Type	llama
Model Files	9.9 GB: 1-of-14 9.7 GB: 2-of-14 9.7 GB: 3-of-14 9.7 GB: 4-of-14 9.7 GB: 5-of-14 9.7 GB: 6-of-14 9.7 GB: 7-of-14 9.7 GB: 8-of-14 9.7 GB: 9-of-14 9.7 GB: 10-of-14 9.7 GB: 11-of-14 9.7 GB: 12-of-14 9.7 GB: 13-of-14 4.1 GB: 14-of-14
Model Architecture	LlamaForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
LoRA Model	Yes
Torch Data Type	float16

Rank the Dromedary 65B Lora HF 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

Quantized Models of the Dromedary 65B Lora HF

Model	Likes	Downloads	VRAM
Dromedary 65B Lora GPTQ	6	6	33 GB

Best Alternatives to Dromedary 65B Lora HF

Best Alternatives	Context / RAM	Downloads	Likes
Kiyo 65M	2K / 0.1 GB	1456	2
Lite Oute 1 65M	2K / 0.3 GB	23	12
Lite Oute 1 65M Instruct	2K / 0.3 GB	15	12
StableBeluga1 Delta	2K / 130.4 GB	146	57
Airoboros 65B Gpt4 M2.0	2K / 130.4 GB	850	0
Airoboros 65B Gpt4 2.0	2K / 130.4 GB	435	0
UltraLM 65B	2K / 130.4 GB	348	9
Openbuddy Llama 65B V8 Bf16	2K / 130.6 GB	177	9
Airoboros 65B Gpt4 1.4	2K / 130.4 GB	163	17
Llama 1 65B Hf	2K / 130.4 GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/dromedary-65b-lora-HF.