Downloads · 30 days
219
6% of all-time downloads
Undi95_-_Xwin-MLewd-13B-V0.2-gguf
RichardErkhov/Undi95_-_Xwin-MLewd-13B-V0.2-gguf
Undi95_-_Xwin-MLewd-13B-V0.2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
3.7K
Public
Repo size
147 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf171 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 25, 2024
- Updated
- Jul 25, 2024
- SHA
- a313ad35
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Xwin-MLewd-13B-V0.2 - GGUF
- Model creator: https://huggingface.co/Undi95/
- Original model: https://huggingface.co/Undi95/Xwin-MLewd-13B-V0.2/
| Name | Quant method | Size |
|---|---|---|
| Xwin-MLewd-13B-V0.2.Q2_K.gguf | Q2_K | 4.52GB |
| Xwin-MLewd-13B-V0.2.IQ3_XS.gguf | IQ3_XS | 4.99GB |
| Xwin-MLewd-13B-V0.2.IQ3_S.gguf | IQ3_S | 5.27GB |
| Xwin-MLewd-13B-V0.2.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| Xwin-MLewd-13B-V0.2.IQ3_M.gguf | IQ3_M | 5.57GB |
| Xwin-MLewd-13B-V0.2.Q3_K.gguf | Q3_K | 5.9GB |
| Xwin-MLewd-13B-V0.2.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| Xwin-MLewd-13B-V0.2.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| Xwin-MLewd-13B-V0.2.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| Xwin-MLewd-13B-V0.2.Q4_0.gguf | Q4_0 | 6.86GB |
| Xwin-MLewd-13B-V0.2.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| Xwin-MLewd-13B-V0.2.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| Xwin-MLewd-13B-V0.2.Q4_K.gguf | Q4_K | 7.33GB |
| Xwin-MLewd-13B-V0.2.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| Xwin-MLewd-13B-V0.2.Q4_1.gguf | Q4_1 | 7.61GB |
| Xwin-MLewd-13B-V0.2.Q5_0.gguf | Q5_0 | 8.36GB |
| Xwin-MLewd-13B-V0.2.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| Xwin-MLewd-13B-V0.2.Q5_K.gguf | Q5_K | 8.6GB |
| Xwin-MLewd-13B-V0.2.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| Xwin-MLewd-13B-V0.2.Q5_1.gguf | Q5_1 | 9.1GB |
| Xwin-MLewd-13B-V0.2.Q6_K.gguf | Q6_K | 9.95GB |
| Xwin-MLewd-13B-V0.2.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description:
license: cc-by-nc-4.0 tags:
- not-for-all-audiences
- nsfw
THIS MODEL IS MADE FOR LEWD
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
This is MLewd merged with Xwin-LM/Xwin-LM-13B-V0.2
<!-- description start -->Description
This repo contains fp16 files of Xwin-MLewd-13B-V0.2, very hot and lewd model based on Xwin 0.2 13B.
<!-- description end --> <!-- description start -->Models and loras used
- Undi95/ReMM-S-Light (base/private)
- Undi95/CreativeEngine
- Brouz/Slerpeno
- The-Face-Of-Goonery/Huginn-v3-13b
- zattio770/120-Days-of-LORA-v2-13B
- PygmalionAI/pygmalion-2-13b
- Undi95/StoryTelling
- TokenBender/sakhi_13B_roleplayer_NSFW_chat_adapter
- nRuaif/Kimiko-v2-13B
- The-Face-Of-Goonery/Huginn-13b-FP16
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
- Xwin-LM/Xwin-LM-13B-V0.2
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
The secret sauce
slices:
- sources:
- model: Xwin-LM/Xwin-LM-13B-V0.2
layer_range: [0, 40]
- model: Undi95/MLewd-v2.4-13B
layer_range: [0, 40]
merge_method: slerp
base_model: Xwin-LM/Xwin-LM-13B-V0.2
parameters:
t:
- filter: lm_head
value: [0.55]
- filter: embed_tokens
value: [0.7]
- filter: self_attn
value: [0.65, 0.35]
- filter: mlp
value: [0.35, 0.65]
- filter: layernorm
value: [0.4, 0.6]
- filter: modelnorm
value: [0.6]
- value: 0.5 # fallback for rest of tensors
dtype: float16
Special thanks to Sushi and Shena ♥
If you want to support me, you can here.
- Created
- Jul 25, 2024
- Updated
- Jul 25, 2024