README.md

---
language:
- en
license: apache-2.0
---

<div align="center">
  <b style="font-size: 30px;">LLAMA-3_8B_Unaligned_Alpha_RP_Soup</b>


</div>


<img src="https://i.imgur.com/pXcjpoV.png" alt="LLAMA-3_8B_Unaligned_Alpha_RP_Soup" style="width: 50%; min-width: 400px; display: block; margin: auto;">


# Model Details
Censorship level: <b>Medium</b>

  
  This model is the outcome of multiple merges, starting with the base model **[SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha)**. The merging process was conducted in several stages:

    Merge 1: LLAMA-3_8B_Unaligned_Alpha was SLERP merged with invisietch/EtherealRainbow-v0.3-8B.
    Merge 2: LLAMA-3_8B_Unaligned_Alpha was SLERP merged with TheDrummer/Llama-3SOME-8B-v2.
    Soup 1: Merge 1 was combined with Merge 2.
    Final Merge: Soup 1 was SLERP merged with Nitral-Archive/Hathor_Enigmatica-L3-8B-v0.4.
  
<details>
<summary>Mergekit configs:</summary>
  
# Merge 1
```yaml
slices:
  - sources:
      - model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
        layer_range: [0, 32]
      - model: BeaverAI/Llama-3SOME-8B-v2d
        layer_range: [0, 32]
merge_method: slerp
base_model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

```

# Merge 2
```yaml
slices:
  - sources:
      - model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
        layer_range: [0, 32]
      - model: invisietch/EtherealRainbow-v0.3-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

```

# Soup 1
```yaml
slices:
  - sources:
      - model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
        layer_range: [0, 32]
      - model: Nitral-Archive/Hathor_Enigmatica-L3-8B-v0.4
        layer_range: [0, 32]
merge_method: slerp
base_model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

```
# Final Merge
```yaml
slices:
  - sources:
      - model: Soup 1
        layer_range: [0, 32]
      - model: Nitral-Archive/Hathor_Enigmatica-L3-8B-v0.4
        layer_range: [0, 32]
merge_method: slerp
base_model: Soup 1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

```
</details>
  
The final model is surprisingly coherent (although slightly more censored), which is a bit unexpected, since all the intermediate merge steps were pretty incoherent. 

## LLAMA-3_8B_Unaligned_Alpha_RP_Soup is available at the following quantizations:

- Original: [FP16](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup)
- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup_GGUF) | [iMatrix_GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_Alpha_RP_Soup-i1-GGUF)
- EXL2: [5.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup_EXL2_5.0bpw) | [6.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup_EXL2_6.0bpw) | [7.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup_EXL2_7.0bpw) | [8.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup_EXL2_8.0bpw)



# Model instruction template: (Can use either ChatML or Llama-3)
# ChatML
```
<|im_start|>system
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
<|im_start|>User request
{prompt}<|im_end|>
<|im_start|>AI answer
```

# Llama-3-Instruct

```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>
```

**Recommended generation Presets:**
<details>
<summary><b>No idea</b>, but sometimes <b>Midnight Enigma</b> gives nice results.</summary>
  max_new_tokens: 512

  temperature: 0.98
  
  top_p: 0.37
  
  top_k: 100
  
  typical_p: 1
  
  min_p: 0
  
  repetition_penalty: 1.18
  
  do_sample: True

  <img src="https://i.imgur.com/rQ7V6OC.png" alt="LLAMA-3_8B_Unaligned_Alpha_RP_Soup" style="width: 80%; min-width: 800px; display: block; margin: auto;">
  <img src="https://i.imgur.com/caL0m8G.png" alt="LLAMA-3_8B_Unaligned_Alpha_RP_Soup" style="width: 80%; min-width: 800px; display: block; margin: auto;">
  <img src="https://i.imgur.com/jyLDlds.png" alt="LLAMA-3_8B_Unaligned_Alpha_RP_Soup" style="width: 80%; min-width: 800px; display: block; margin: auto;">

</details>

*Sometimes the model might output a text that's too long.


## The base model used for the merge - LLAMA-3_8B_Unaligned_Alpha - is available at the following quantizations:

Censorship level: <b>Low - Medium</b>

- Original: [FP16](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha)
- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_GGUF) | [iMatrix_GGUF](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF)
- EXL2: [2.6 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_2.6bpw) | [3.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_3.0bpw) | [3.5 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_3.5bpw) | [4.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_4.0bpw) | [4.5 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_4.5bpw) | [5.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_5.0bpw)  | [5.5 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_5.5bpw) | [6.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_6.0bpw) | [6.5 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_6.5bpw) | [7.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_7.0bpw) | [7.5 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_7.5bpw) | [8.0 bpw](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_EXL2_8.0bpw)


### Support
<img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;">

- [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻
- [My Patreon](https://patreon.com/TenebraAI) ALL donations will go for research resources and compute, every bit appreciated 🙏🏻

## Other stuff
- [Experemental TTS extension for oobabooga](https://github.com/SicariusSicariiStuff/Diffusion_TTS) Based on Tortoise, EXTREMELY good quality, IF, and that's a big if, you can make it to work!
- [Demonstration of the TTS capabilities](https://www.youtube.com/watch?v=V6ewxU6c1W8) Charsi narrates her story, Diablo2 (18+)
- [Tenebra 30B](https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_FP16) My original Tenebra model, very unique, 'self aware', very uncensored.
- [Tenebra 13B](https://huggingface.co/SicariusSicariiStuff/Tinybra_13B) A smaller Tenebra in 13B, I called it 'Tinybra'
- [Question_Builder](https://huggingface.co/SicariusSicariiStuff/Question_Builder) A small, highly useful model to help our open source community in generating new datasets. It returns a single question based on any input.