What are the hardware requirements for Dark Miqu 103B?

Dark Miqu 103B requires approximately 206.4 GB of VRAM and supports a context window of 31K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dark Miqu 103B and how large is it?

Dark Miqu 103B is developed by jukofyork, a model with 103b 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 Dark Miqu 103B?

Dark Miqu 103B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dark Miqu 103B by jukofyork — VRAM 206.4GB, 31K context

Name: Dark Miqu 103B
Author: jukofyork

Dark Miqu 103B is an open-source language model by jukofyork. Features: 103b LLM, VRAM: 206.4GB, Context: 31K, License: other, Merged, LLM Explorer Score: 0.12.

Merged Model Autotrain compatible Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jukofyork/Dark-Miqu-103B

Dark Miqu 103B Parameters and Internals

Model Type

self-merge

Additional Notes

Created using [Mergekit](https://github.com/arcee-ai/mergekit).

Input Output

Input Format:

Vicuna format: `USER: {prompt} ASSISTANT: `

Output Format:

The output format corresponding to the input Vicuna format.

LLM Name	Dark Miqu 103B
Repository 🤗	https://huggingface.co/jukofyork/Dark-Miqu-103B
Merged Model	Yes
Model Size	103b
Required VRAM	206.4 GB
Updated	2024-12-03
Maintainer	jukofyork
Model Type	llama
Model Files	9.6 GB: 1-of-21 10.0 GB: 2-of-21 9.9 GB: 3-of-21 10.0 GB: 4-of-21 9.8 GB: 5-of-21 9.9 GB: 6-of-21 9.8 GB: 7-of-21 9.7 GB: 8-of-21 10.0 GB: 9-of-21 9.9 GB: 10-of-21 9.8 GB: 11-of-21 9.9 GB: 12-of-21 9.7 GB: 13-of-21 9.8 GB: 14-of-21 9.8 GB: 15-of-21 9.8 GB: 16-of-21 9.8 GB: 17-of-21 10.0 GB: 18-of-21 9.9 GB: 19-of-21 9.8 GB: 20-of-21 9.5 GB: 21-of-21
Model Architecture	LlamaForCausalLM
License	other
Context Length	32764
Model Max Length	32764
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Dark Miqu 103B 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 Dark Miqu 103B

Best Alternatives	Context / RAM	Downloads	Likes
BigWeave V15 103B	31K / 206.6 GB	85	2
Midnight Miqu 103B V1.5	31K / 206.4 GB	33	28
Midnight Miqu 103B V1.0	31K / 206.4 GB	85	16
Midnight Rose 103B V2.0.3	4K / 206.6 GB	93	13
OmegaDolphin 103B V0.1	4K / 175.6 GB	6	1
KitchenSink 103b	4K / 178.6 GB	13	9
Midnight Rose 103B V1.0	4K / 206.6 GB	11	3
Aurora Nights 103B V1.0	4K / 206.6 GB	6	14
Rogue Rose 103B V0.2	4K / 206.5 GB	12	33
Lila 103B L2	4K / 206.2 GB	0	0