|
--- |
|
license: apache-2.0 |
|
--- |
|
**Exllamav2** quant (**exl2** / **8.0 bpw**) made with ExLlamaV2 v0.1.1 |
|
|
|
Other EXL2 quants: |
|
| **Quant** | **Model Size** | **lm_head** | |
|
| ----- | ---------- | ------- | |
|
|<center>**[2.2](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-2_2bpw_exl2)**</center> | <center>3588 MB</center> | <center>6</center> | |
|
|<center>**[2.5](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-2_5bpw_exl2)**</center> | <center>3990 MB</center> | <center>6</center> | |
|
|<center>**[3.0](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-3_0bpw_exl2)**</center> | <center>4718 MB</center> | <center>6</center> | |
|
|<center>**[3.5](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-3_5bpw_exl2)**</center> | <center>5443 MB</center> | <center>6</center> | |
|
|<center>**[3.75](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-3_75bpw_exl2)**</center> | <center>5809 MB</center> | <center>6</center> | |
|
|<center>**[4.0](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-4_0bpw_exl2)**</center> | <center>6166 MB</center> | <center>6</center> | |
|
|<center>**[4.25](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-4_25bpw_exl2)**</center> | <center>6537 MB</center> | <center>6</center> | |
|
|<center>**[5.0](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-5_0bpw_exl2)**</center> | <center>7625 MB</center> | <center>6</center> | |
|
|<center>**[6.0](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-6_0bpw_exl2)**</center> | <center>9111 MB</center> | <center>8</center> | |
|
|<center>**[6.5](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-6_5bpw_exl2)**</center> | <center>9831 MB</center> | <center>8</center> | |
|
|<center>**[8.0](https://huggingface.co/Zoyd/Ppoyaa_LuminRP-13B-128k-v0.5-8_0bpw_exl2)**</center> | <center>11277 MB</center> | <center>8</center> | |
|
|
|
# LuminRP-13B-128k-v0.5 |
|
LuminRP-13B-128k-v0.5 is the 13B parameter version of the v0.5, LuminRP-7B model which specializes in RP/ERP by merging a couple models that excels in it. |
|
*** |
|
>[!IMPORTANT] |
|
> * Link to [Ppoyaa/LuminRP-7B-128k-v0.5](https://huggingface.co/Ppoyaa/LuminRP-7B-128k-v0.5) |
|
|
|
> * This model can and will output X-rated content. |
|
*** |
|
## SillyTavern |
|
**Template**: Alpaca, ChatML, and Mistral should be okay. |
|
|
|
**Instruct Mode**: On |
|
*** |
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Ppoyaa/LuminRP-13B-128k-v0.5" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
*** |
|
Merge Details Below: |
|
|
|
<details><summary>See Merge Config</summary> |
|
|
|
``` |
|
ChaoticNeutrals/BuRP_7B |
|
Endevor/InfinityRP-v1-7B |
|
Nitral-AI/Kunocchini-7b-128k-test |
|
core-3/kuno-royale-v2-7b |
|
KatyTheCutie/LemonadeRP-4.5.3 |
|
grimjim/kukulemon-7B |
|
MaziyarPanahi/Calme-7B-Instruct-v0.9 |
|
icefog72/WestIceLemonTeaRP-32k-7b |
|
crestf411/daybreak-kunoichi-2dpo-7b |
|
Undi95/Mistral-RP-0.1-7B |
|
``` |
|
</details><br> |
