What are the hardware requirements for Limarpv3 Llama2 70B Qlora?

Limarpv3 Llama2 70B Qlora requires approximately 1.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Limarpv3 Llama2 70B Qlora and how large is it?

Limarpv3 Llama2 70B Qlora is developed by Doctor-Shotgun, 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 Limarpv3 Llama2 70B Qlora?

Limarpv3 Llama2 70B Qlora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Limarpv3 Llama2 70B Qlora by Doctor-Shotgun — VRAM 1.7GB

Name: Limarpv3 Llama2 70B Qlora
Author: Doctor-Shotgun

Limarpv3 Llama2 70B Qlora is an open-source language model by Doctor-Shotgun. Features: 70b LLM, VRAM: 1.7GB, License: apache-2.0, LLM Explorer Score: 0.1.

4-bit Autotrain compatible Bitsandbytes Endpoints compatible Generated from trainer Llama Lora Region:us

Model Card on HF 🤗: https://huggingface.co/Doctor-Shotgun/limarpv3-llama2-70b-qlora

Limarpv3 Llama2 70B Qlora Parameters and Internals

Model Type

roleplaying, chat

Use Cases

Primary Use Cases:

longform-oriented, novel-style roleplaying chat model intended to replicate the experience of 1-on-1 roleplay on Internet forums.

Limitations:

Short-form, IRC/Discord-style RP (aka "Markdown format") is not supported., The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model.

Additional Notes

General format and functionality inspired by the previously named "Roleplay" preset in SillyTavern.

Training Details

Data Sources:

LimaRP v3 dataset

Methodology:

Training without the pretraining stage using stories. Does not include instruction tuning, only manually picked and slightly edited RP conversations with persona and scenario data.

Input Output

Input Format:

Extended Alpaca format

Performance Tips:

Use length modifier in response instruction sequence for better control over response length.

LLM Name	Limarpv3 Llama2 70B Qlora
Repository 🤗	https://huggingface.co/Doctor-Shotgun/limarpv3-llama2-70b-qlora
Model Size	70b
Required VRAM	1.7 GB
Updated	2025-09-28
Maintainer	Doctor-Shotgun
Model Files	1.7 GB
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|v_proj\|gate_proj\|down_proj\|k_proj\|up_proj\|q_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	32

Rank the Limarpv3 Llama2 70B 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 Limarpv3 Llama2 70B Qlora

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.1 Tango 70B	0K / 3 GB	6	8
LLama3 70B SWE LLM	0K / 16.1 GB	3	1
Limarpv3 Llama2 70B Qlora	0K / 1.7 GB	16	2
Llama 2 70B Chat Longlora 32K	0K / 0.1 GB	6	9
Nous Hermes Llama2 70B	0K / 138 GB	144	84
Llama 2 70B Longlora 32K	0K / 0.1 GB	6	18
... 70M Instruct Orca Chkpt 64000	0K / 0.2 GB	8	1
NorskGPT Llama 3 70B Adapter	0K / 0.2 GB	6	7
Llama 3 70B Tagengo	0K / 141.9 GB	3	1
...3 70B Instruct Uncensored Lora	0K / 0.8 GB	8	3

Note: green Score (e.g. "73.2") means that the model is better than Doctor-Shotgun/limarpv3-llama2-70b-qlora.