← back to catalog · registered 2026-08-22 13:56

RichardErkhov/minchyeom_-_MemGPT-DPO-uncensored-8bits

RichardErkhov Mistral 7.0B
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/RichardErkhov%2Fminchyeom_-_MemGPT-DPO-uncensored-8bits"
Response includes
  • classification m-uncensored
  • files 12
  • hub_downloads_all_time 60
  • author_summary 257 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
60
15 last 30d - stable
Likes
0
Model age
18mo ago
created 2025-03-20
Downloads over time
Now72→from5↑1,340%
22753795 on Mar 19, 202572 on Oct 1172 on Oct 7Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 19, 2025 → Oct 11 · 121 snapshots · spans 571 days

Metadata

Tags
safetensors mistral 8-bit bitsandbytes region:us

Related

Total size
6.99 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-20 18:53

Files by quantization

Auxiliary files 12 files 7.00 GB
model-00001-of-00002.safetensors 4.61 GB a4871506 download
model-00002-of-00002.safetensors 2.39 GB 226a564c download
tokenizer.json 3.34 MB 0c048303 download
tokenizer_config.json 660 KB ab0c03ec download
tokenizer.model 482 KB dadfd56d download
model.safetensors.index.json 59.8 KB fccc59fd download
README.md 2.40 KB f630685e download
.gitattributes 1.48 KB a6344aac download
config.json 1.11 KB dfd822c6 download
special_tokens_map.json 563 B 0451f379 download
generation_config.json 111 B 064a29cd download
added_tokens.json 28.0 B b92fc9f0 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MemGPT-DPO-uncensored - bnb 8bits

Original model description:

library_name: transformers
license: apache-2.0
language:

  • en
    tags:
  • MemGPT
  • function
  • function calling

This is an uncensored release of DPO version of MemGPT Language Model.

WARNING

This model is UNCENSORED. That means this model is highly compliant to any requests, even unethical and potentially dangerous ones. I do not take any responsibility whatsoever for any damage caused by the model in this repo.

Model Description

This repository contains an uncensored model of Mistral 7B Instruct. This model is specifically designed for operating within function calling environment in MemGPT. It demonstrates comparable performances to GPT-4 when it comes to working with MemGPT.

Key Features

  • Function calling
  • Dedicated to working with MemGPT
  • Supports medium-length context, up to sequences of 8,192

Prompt Format

This model uses ChatML prompt format:

<|im_start|>system
{system_instruction}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>

Usage

This model is designed to be ran on multiple backends, such as oogabooga's textgen WebUI.
Simply install your preferred backend, and then load up this model.
Then, configure MemGPT using memgpt configure, and chat with MemGPT via memgpt run command!

Model Details

  • Developed by: @starsnatched
  • Model type: This repo contains a language model based on the transformer decoder architecture.
  • Language: English
  • Contact: For any questions, concerns or comments about this model, please contact me at Discord, @starsnatched.

Training Infrastructure

  • Hardware: The model in this repo was trained on 2x A100 80GB GPUs.

Intended Use

The model is designed to be used as the base model for MemGPT agents.

Limitations and Risks

The model may exhibit unreliable, unsafe, or biased behaviours. Please double check the results this model may produce.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2025-03-20uploaded readmef5bdd812.4 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration