Downloads · 30 days
384
8% of all-time downloads
maldv_-_dragonwar-7b-alpha-gguf
RichardErkhov/maldv_-_dragonwar-7b-alpha-gguf
maldv_-_dragonwar-7b-alpha-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
4.7K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024
- SHA
- d8ecf381
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
dragonwar-7b-alpha - GGUF
- Model creator: https://huggingface.co/maldv/
- Original model: https://huggingface.co/maldv/dragonwar-7b-alpha/
| Name | Quant method | Size |
|---|---|---|
| dragonwar-7b-alpha.Q2_K.gguf | Q2_K | 2.53GB |
| dragonwar-7b-alpha.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| dragonwar-7b-alpha.IQ3_S.gguf | IQ3_S | 2.96GB |
| dragonwar-7b-alpha.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| dragonwar-7b-alpha.IQ3_M.gguf | IQ3_M | 3.06GB |
| dragonwar-7b-alpha.Q3_K.gguf | Q3_K | 3.28GB |
| dragonwar-7b-alpha.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| dragonwar-7b-alpha.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| dragonwar-7b-alpha.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| dragonwar-7b-alpha.Q4_0.gguf | Q4_0 | 3.83GB |
| dragonwar-7b-alpha.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| dragonwar-7b-alpha.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| dragonwar-7b-alpha.Q4_K.gguf | Q4_K | 4.07GB |
| dragonwar-7b-alpha.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| dragonwar-7b-alpha.Q4_1.gguf | Q4_1 | 4.24GB |
| dragonwar-7b-alpha.Q5_0.gguf | Q5_0 | 4.65GB |
| dragonwar-7b-alpha.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| dragonwar-7b-alpha.Q5_K.gguf | Q5_K | 4.78GB |
| dragonwar-7b-alpha.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| dragonwar-7b-alpha.Q5_1.gguf | Q5_1 | 5.07GB |
| dragonwar-7b-alpha.Q6_K.gguf | Q6_K | 5.53GB |
| dragonwar-7b-alpha.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
library_name: transformers tags:
- unsloth
- book license: cc-by-nc-4.0
Dragonwar 7b - α
The time of the great dragon war is upon us! How many different fantasy novels? One hundred and seventeen you say?
Trained with full text windows, followed by completion, followed by ORPO, followed by one more epoch of the full text, rotated 1/4 in the window. That last train settled everything down and it seems quite coherent.
How to Use
This is not a chat model, but intended for storymode or similar. No prompt, but start with a bit of story, or a name.
*** Prologue
The sun rose
Authors notes are highly effective. You can use an authors note of something like:
[King Robb Stark and Lord Rahl are at war.]
You have quite a cast of characters to draw from. Perhaps Perrin makes a stop by the Waystone Inn, or Zeddicus and Gandalf have a smoke together.
Settings
I usually use Min-P of 0.1, dynatemp between 0.5 and 2, and smoothing between 0.05 and 0.2.
Hacks
To get rid of unwanted EOS's, I did the following...
import torch
result_dict : dict[str, torch.Tensor] = model.state_dict()
result_dict['lm_head.weight'][2] = 0
model.state_dict = lambda : result_dict
So now there are no EOS's at all, ever.
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024