LLM EXPLORER 59,420 MODELS INDEXED

NSFW DPO Vmgb 7B by athirdpath

By athirdpath · 11 downloads
HF Repo ↗ Copy URL

NSFW DPO Vmgb 7B is an open-source language model by athirdpath. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: cc-by-nc-4.0, Merged, LLM Explorer Score: 0.1.

  Merged Model Dataset:athirdpath/dpo pairs-r... Dataset:athirdpath/dpo pairs-r...   En   Endpoints compatible   Mistral   Not-for-all-audiences   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/athirdpath/NSFW_DPO_vmgb-7b 

NSFW DPO Vmgb 7B Parameters and Internals

Supported Languages 
en (Proficient)
Training Details 
Data Sources:
athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v2, athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
Methodology:
Trained for an epoch on NSFW_DPO-v1 dataset, followed by some LoRA state training until crash on DPO-v2 dataset, then another epoch of NSFW_DPO-v1 dataset.
LLM NameNSFW DPO Vmgb 7B
Repository 🤗https://huggingface.co/athirdpath/NSFW_DPO_vmgb-7b 
Merged ModelYes
Model Size7b
Required VRAM14.4 GB
Updated2026-08-06
Maintainerathirdpath
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to NSFW DPO Vmgb 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB22020
MegaBeam Mistral 7B 512K512K / 14.4 GB847054
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB801817
Hebrew Mistral 7B 200K256K / 30 GB2315
Astral 256K 7B250K / 14.4 GB90
Astral 256K 7B V2250K / 14.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than athirdpath/NSFW_DPO_vmgb-7b.