|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
|
|
<div align="center"> |
|
<b style="font-size: 40px;">Impish_LLAMA_3B</b> |
|
|
|
|
|
</div> |
|
|
|
|
|
<img src="https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B/resolve/main/Images/Impish_LLAMA_3B.png" alt="Dusk Impish_LLAMA_3B" style="width: 70%; min-width: 500px; display: block; margin: auto;"> |
|
|
|
|
|
"With that naughty impish grin of hers, so damn sly it could have ensnared the devil himself, and that impish glare in her eyes, sharper than of a succubus fang, she chuckled impishly with such mischief that even the moon might’ve blushed. I needed no witch's hex to divine her nature—she was, without a doubt, a naughty little imp indeed." |
|
|
|
# Model Details |
|
|
|
|
|
- Censorship level: <b>Low</b> |
|
|
|
- PENDING / 10 (10 completely uncensored) |
|
|
|
- Intended use: **Role-Play**, General tasks. |
|
|
|
"I want some legit RP models of LLAMA 3.2 3B, we got phones!" |
|
|
|
"So make one." |
|
|
|
"K." |
|
|
|
|
|
This model was trained on ~25M tokens, in **3 phases**, the first and longest phase was an FFT to teach the model new stuff, and to confuse the shit out of it too, so it would be **a little bit less inclined to use GPTisms**. |
|
|
|
It worked pretty well. In fact, the model was so damn confused, that the little imp didn't even make sense, but the knowledge was there. |
|
|
|
In the next phase, a DEEP QLORA of **R = 512** was used on a new dataset, to... unconfuse it. A completely different dataset was used to avoid overfitting. |
|
|
|
Finally, another somewhat deep QLORA of **R = 128** was used to tie it all together in a coherent way, and connect all the dots, and this was also with a different dataset as well. |
|
|
|
The results are **sometimes** surprisingly good, it even managed to fool some people into thinking it's a MUCH larger model, and sometimes... sometimes it behaves just like you would expect a 3B model. |
|
|
|
Fun fact: the model was uploaded while there were 200 ICBMs headed my way, live in the sky. |
|
|
|
I lived, so expect more models in the future. |
|
|
|
## Impish_LLAMA_3B is available at the following quantizations: |
|
|
|
- Original: [FP16](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B) |
|
- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_GGUF) | [iMatrix_GGUF](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_iMatrix) |
|
- EXL2: [4.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-4.0bpw) | [5.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-5.0bpw) | [6.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-6.0bpw) | [7.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-7.0bpw) | [8.0 bpw](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B-EXL2-8.0bpw) |
|
- Specialized: [FP8](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_FP8) |
|
- Mobile (ARM): [Q4_0_X_X](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_3B_ARM) |
|
|
|
|
|
|
|
|
|
|
|
|
|
# Model instruction template: 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>Midnight Enigma</b></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 |
|
|
|
</details> |
|
|
|
<details> |
|
<summary><b>min_p</b></summary> |
|
max_new_tokens: 512 |
|
|
|
temperature: 1 |
|
|
|
top_p: 1 |
|
|
|
top_k: 0 |
|
|
|
typical_p: 1 |
|
|
|
min_p: 0.05 |
|
|
|
repetition_penalty: 1 |
|
|
|
do_sample: True |
|
|
|
</details> |
|
|
|
<details> |
|
<summary><b>Divine Intellect</b></summary> |
|
max_new_tokens: 512 |
|
|
|
temperature: 1.31 |
|
|
|
top_p: 0.14 |
|
|
|
top_k: 49 |
|
|
|
typical_p: 1 |
|
|
|
min_p: 0 |
|
|
|
repetition_penalty: 1.17 |
|
|
|
do_sample: True |
|
|
|
</details> |
|
|
|
<details> |
|
<summary><b>simple-1</b></summary> |
|
max_new_tokens: 512 |
|
|
|
temperature: 0.7 |
|
|
|
top_p: 0.9 |
|
|
|
top_k: 20 |
|
|
|
typical_p: 1 |
|
|
|
min_p: 0 |
|
|
|
repetition_penalty: 1.15 |
|
|
|
do_sample: True |
|
|
|
</details> |
|
|
|
|
|
|
|
### 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 🙏🏻 |
|
|
|
## Other stuff |
|
- [Blog and updates](https://huggingface.co/SicariusSicariiStuff/Blog_And_Updates) Some updates, some rambles, sort of a mix between a diary and a blog. |
|
- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector. |
|
- [LLAMA-3_8B_Unaligned](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned) The grand project that started it all. |
