---
license: llama3
language:
- en
- ja
- zh
tags:
  - roleplay
  - llama3
  - sillytavern
  - idol
---
# Special Thanks:
 - Lewdiculous's superb gguf version, thank you for your conscientious and responsible dedication.
 - https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF-IQ-Imatrix-Request
 - mradermacher's superb gguf version, thank you for your conscientious and responsible dedication.
 - https://huggingface.co/mradermacher/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF
# These are my own quantizations (updated almost daily).
The difference with normal quantizations is that I quantize the output and embed tensors to f16.
and the other tensors to 15_k,q6_k or q8_0.
This creates models that are little or not degraded at all and have a smaller size.
They run at about 3-6 t/sec on CPU only using llama.cpp
And obviously faster on computers with potent GPUs

- the fast cat at [ZeroWw/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF](https://huggingface.co/ZeroWw/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF)

## Why 1048K? 
Due to the optimization of the preferred model, its performance is excellent across the range of 2000-1048K. Personal usage scenarios, such as 8186, 32K, etc., are insufficient. My primary role involves managing virtual idol Twitter accounts and assisting with singing, etc. A good conversation can be very lengthy, and sometimes even 32K is not enough. Imagine having a heated chat with your virtual girlfriend, only for it to abruptly cut off—that feeling is too painful. 

## What kind of graphics card is needed? 
For investing in a girlfriend, would a 4090 or higher be more of a question?

## virtual idol Twitter
- https://x.com/aifeifei799

# Model Description:
The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.

- Saving money(LLama 3)
- Uncensored
- Quick response
- The underlying model used is winglian/Llama-3-8b-1048k-PoSE
- A scholarly response akin to a thesis.(I tend to write songs extensively, to the point where one song almost becomes as detailed as a thesis. :)
- DarkIdol:Roles that you can imagine and those that you cannot imagine.
- Roleplay
- Specialized in various role-playing scenarios
- more look at test role. (https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2/tree/main/test) 
- more look at LM Studio presets (https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2/tree/main/config-presets)

![image/png](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K/resolve/main/llama3-8B-DarkIdol-2.2-Uncensored-1048K.png)

# Chang Log
### 2024-07-01
- add writer and more RP
- Optimize Japanese
- Optimize logical processing
- More humanized

### 2024-06-26
- 1048K

![image/png](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K/resolve/main/llama3-8B-DarkIdol-2.2-Uncensored-1048K.jpg)

# Questions
- The model's response results are for reference only, please do not fully trust them.
- testing with other tools is not comprehensive.but there may be new issues, so please leave a message if you encounter any.


# 问题
- 模型回复结果仅供参考,请勿完全相信
- 工具的测试不完善

# Stop Strings
```python
    stop = [
      "## Instruction:",
      "### Instruction:",
      "<|end_of_text|>",
      "  //:",
      "</s>",
      "<3```",
      "### Note:",
      "### Input:",
      "### Response:",
      "### Emoticons:"
    ],
```
# Model Use
- Koboldcpp https://github.com/LostRuins/koboldcpp
- Since KoboldCpp is taking a while to update with the latest llama.cpp commits, I'll recommend this [fork](https://github.com/Nexesenex/kobold.cpp) if anyone has issues.
- LM Studio https://lmstudio.ai/
- llama.cpp https://github.com/ggerganov/llama.cpp
- Backyard AI https://backyard.ai/
- Meet Layla,Layla is an AI chatbot that runs offline on your device.No internet connection required.No censorship.Complete privacy.Layla Lite https://www.layla-network.ai/
- Layla Lite llama3-8B-DarkIdol-1.1-Q4_K_S-imat.gguf https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-2.2-Uncensored-1048K/blob/main/llama3-8B-DarkIdol-2.2-Uncensored-1048K-Q4_K_S-imat.gguf?download=true
- more gguf at https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF-IQ-Imatrix-Request
# character
- https://character-tavern.com/
- https://characterhub.org/
- https://pygmalion.chat/
- https://aetherroom.club/
- https://backyard.ai/
- Layla AI chatbot
### If you want to use vision functionality:
 * You must use the latest versions of [Koboldcpp](https://github.com/Nexesenex/kobold.cpp).
 
### To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16)
 
 * You can load the **mmproj** by using the corresponding section in the interface:
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
### Thank you:
 To the authors for their hard work, which has given me more options to easily create what I want. Thank you for your efforts.
- Hastagaras
- Gryphe
- cgato
- ChaoticNeutrals
- mergekit
- merge
- transformers
- llama
- Nitral-AI
- MLP-KTLim
- rinna
- hfl
- Rupesh2
- stephenlzc
- theprint
- Sao10K
- turboderp
- TheBossLevel123
- winglian
- .........

---
base_model:
- turboderp/llama3-turbcat-instruct-8b
- winglian/llama-3-8b-1m-PoSE
- Sao10K/L3-8B-Stheno-v3.3-32K
- Hastagaras/Jamet-8B-L3-MK.V-Blackroot
- vicgalle/Roleplay-Llama-3-8B
- Nitral-AI/Hathor_Fractionate-L3-8B-v.05
library_name: transformers
tags:
- mergekit
- merge

---
# llama3-8B-DarkIdol-2.2-Uncensored-1048K-a

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [winglian/llama-3-8b-1m-PoSE](https://huggingface.co/winglian/llama-3-8b-1m-PoSE) as a base.

### Models Merged

The following models were included in the merge:
* [turboderp/llama3-turbcat-instruct-8b](https://huggingface.co/turboderp/llama3-turbcat-instruct-8b)
* [Sao10K/L3-8B-Stheno-v3.3-32K](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.3-32K)
* [Hastagaras/Jamet-8B-L3-MK.V-Blackroot](https://huggingface.co/Hastagaras/Jamet-8B-L3-MK.V-Blackroot)
* [vicgalle/Roleplay-Llama-3-8B](https://huggingface.co/vicgalle/Roleplay-Llama-3-8B)
* [Nitral-AI/Hathor_Fractionate-L3-8B-v.05](https://huggingface.co/Nitral-AI/Hathor_Fractionate-L3-8B-v.05)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
#base
  - model: Sao10K/L3-8B-Stheno-v3.3-32K
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - model: Nitral-AI/Hathor_Fractionate-L3-8B-v.05
  - model: turboderp/llama3-turbcat-instruct-8b
  - model: vicgalle/Roleplay-Llama-3-8B
  - model: winglian/llama-3-8b-1m-PoSE
merge_method: model_stock
base_model: winglian/llama-3-8b-1m-PoSE
dtype: bfloat16

```


---
base_model:
- maldv/llama-3-fantasy-writer-8b
- hfl/llama-3-chinese-8b-instruct-v3
- elyza/Llama-3-ELYZA-JP-8B
- MLP-KTLim/llama-3-Korean-Bllossom-8B
library_name: transformers
tags:
- mergekit
- merge

---
# llama3-8B-DarkIdol-2.2-Uncensored-1048K-b

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-a as a base.

### Models Merged

The following models were included in the merge:
* [maldv/llama-3-fantasy-writer-8b](https://huggingface.co/maldv/llama-3-fantasy-writer-8b)
* [hfl/llama-3-chinese-8b-instruct-v3](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v3)
* [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B)
* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
#writer
#  - model: openerotica/Llama-3-lima-nsfw-16k-test 不兼容
  - model: maldv/llama-3-fantasy-writer-8b
#lang
  - model: hfl/llama-3-chinese-8b-instruct-v3
  - model: elyza/Llama-3-ELYZA-JP-8B
  - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
  - model: ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-a
merge_method: model_stock
base_model: ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-a
dtype: bfloat16

```



---
base_model:
- aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
- TheBossLevel123/Llama3-Toxic-8B-Float16
library_name: transformers
tags:
- mergekit
- merge

---
# llama3-8B-DarkIdol-2.2-Uncensored-1048K

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-b as a base.

### Models Merged

The following models were included in the merge:
* [aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K)
* [TheBossLevel123/Llama3-Toxic-8B-Float16](https://huggingface.co/TheBossLevel123/Llama3-Toxic-8B-Float16)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
#uncensored
  - model: TheBossLevel123/Llama3-Toxic-8B-Float16
  - model: aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K
  - model: ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-b
merge_method: model_stock
base_model: ./llama3-8B-DarkIdol-2.2-Uncensored-1048K-b
dtype: bfloat16

```