Name: AshhLimaRP Mistral 7B
Author: lemonilia

AshhLimaRP Mistral 7B is an open-source language model by lemonilia. Features: 7b LLM, VRAM: 14.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

Endpoints compatible Gguf Lora Mistral Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B

AshhLimaRP Mistral 7B Benchmarks

LLME Score: 0.10155

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

AshhLimaRP Mistral 7B (lemonilia/AshhLimaRP-Mistral-7B)

🌟 Advertise your project 🚀

AshhLimaRP Mistral 7B Parameters and Internals

Model Type

Roleplaying chat model

Use Cases

Areas:

Roleplaying, Longform-oriented novel-style chat

Primary Use Cases:

1-on-1 roleplay on Internet forums

Limitations:

Short-form, IRC/Discord-style RP not supported, Can ramble or impersonate user with very long messages, No instruction tuning

Additional Notes

The model features a length control mechanism inspired by 'Roleplay' preset in SillyTavern.

Training Details

Data Sources:

2000 training samples up to about 9k tokens length, human-written lewd stories

Methodology:

Finetuned on Ashhwriter, a model based on human-written lewd stories, with manually picked and slightly edited RP conversations.

Context Length:

8750

Hardware Used:

2x NVidia A40 GPUs

Input Output

Input Format:

Extended Alpaca format

Accepted Modalities:

text

Output Format:

Extended Alpaca format

Performance Tips:

Use length modifiers (e.g., 'medium') to control response length.

Release Notes

Version:

Notes:

Initial release based on Ashhwriter-Mistral-7B training.

LLM Name	AshhLimaRP Mistral 7B
Repository 🤗	https://huggingface.co/lemonilia/AshhLimaRP-Mistral-7B
Model Size	7b
Required VRAM	14.4 GB
Updated	2025-12-08
Maintainer	lemonilia
Model Files	4.4 GB 5.9 GB 2.7 GB 4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Is Biased	none
Tokenizer Class	LlamaTokenizer
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|gate_proj\|v_proj\|q_proj\|o_proj\|up_proj\|down_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	256

Quantized Models of the AshhLimaRP Mistral 7B

Model	Likes	Downloads	VRAM
AshhLimaRP Mistral 7B GGUF	2	312	3 GB
AshhLimaRP Mistral 7B GPTQ	3	5	4 GB
AshhLimaRP Mistral 7B AWQ	2	7	4 GB

Best Alternatives to AshhLimaRP Mistral 7B

Best Alternatives	Context / RAM	Downloads	Likes
ShoriRP V0.75d	0K / 0.2 GB	52	33
...wen Math 7b 24 1 100 1 Nonmath	0K / 15.2 GB	21	0
ReWiz 7B	0K / 14.5 GB	112	0
CleverBoi 7B V3	0K / 0.2 GB	112	0
Mistral 7B V0.1 Hitl	0K / 14.4 GB	8	0
...rendyol 7B Base V1 MtLoRA Entr	0K / 14.6 GB	62	0
Mistral Llm V4	0K / 14.4 GB	13	0
Gemma 7B English To Hinglish	0K / 17.1 GB	37	0
...rix Philosophy Mistral 7B LoRA	0K / 14.4 GB	375	9
Gumzo Llama 00	0K / 0.3 GB	30	0

Note: green Score (e.g. "73.2") means that the model is better than lemonilia/AshhLimaRP-Mistral-7B.

Rank the AshhLimaRP Mistral 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53127 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

AshhLimaRP Mistral 7B by lemonilia

» All LLMs » lemonilia » AshhLimaRP Mistral 7B URL Share it on