What are the hardware requirements for Miqu 1 70B Hermes2.5 Qlora?

Miqu 1 70B Hermes2.5 Qlora requires approximately 4.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Miqu 1 70B Hermes2.5 Qlora and how large is it?

Miqu 1 70B Hermes2.5 Qlora is developed by 152334H, a model with 70b 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 Miqu 1 70B Hermes2.5 Qlora?

Miqu 1 70B Hermes2.5 Qlora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Miqu 1 70B Hermes2.5 Qlora by 152334H — VRAM 4.8GB

Name: Miqu 1 70B Hermes2.5 Qlora
Author: 152334H

Miqu 1 70B Hermes2.5 Qlora is an open-source language model by 152334H. Features: 70b LLM, VRAM: 4.8GB, LLM Explorer Score: 0.11.

4-bit Adapter Base model:152334h/miqu-1-70b-... Base model:adapter:152334h/miq... Bitsandbytes Finetuned Generated from trainer Llama Lora Peft Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/152334H/miqu-1-70b-hermes2.5-qlora

Miqu 1 70B Hermes2.5 Qlora Parameters and Internals

Model Type

LlamaForCausalLM

Additional Notes

Fine-tuned using peft library version 0.4.0, Transformers 4.38.0.dev0, Pytorch 2.2.0+cu121, Datasets 2.16.1, and Tokenizers 0.15.0.

Training Details

Data Sources:

teknium/OpenHermes-2.5

Methodology:

This model uses the QLoRA method for fine-tuning.

Context Length:

4096

LLM Name	Miqu 1 70B Hermes2.5 Qlora
Repository 🤗	https://huggingface.co/152334H/miqu-1-70b-hermes2.5-qlora
Base Model(s)	Miqu 1 70B Sf 152334H/miqu-1-70b-sf
Model Size	70b
Required VRAM	4.8 GB
Updated	2025-01-22
Maintainer	152334H
Model Files	4.8 GB
Model Architecture	Adapter
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|up_proj\|o_proj\|down_proj\|gate_proj\|q_proj\|v_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	32

Rank the Miqu 1 70B Hermes2.5 Qlora 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 Miqu 1 70B Hermes2.5 Qlora

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.1 70B Abliterated Lora	0K / 1.7 GB	72	4
...aiga Llama3 70b Sft M1 D5 Lora	0K / 5.9 GB	0	1
Llama 3 70B Instruct Spider	0K / 141.9 GB	6	0
Airoboros 70B 3.3 Peft	0K / 0.4 GB	0	2
Llama3v1	0K / 0.1 GB	5	0
Xwin LM 70B V0.1 LORA	0K / 1.7 GB	6	1
Euryale 1.3 L2 70B LORA	0K / 1.7 GB	8	1
Miqu Limarp 70B DPO Safefile	0K / 38.4 GB	5	1
Limarp Miqu 1 70B Qlora	0K / 1.7 GB	5	4
Limarp Miqu 1 70B Qlora	0K / 1.7 GB	2	4

Note: green Score (e.g. "73.2") means that the model is better than 152334H/miqu-1-70b-hermes2.5-qlora.