Add README.md content description
Browse files
README.md
CHANGED
@@ -1,3 +1,95 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
inference: false
|
4 |
+
library_name: llama.cpp
|
5 |
+
license: cc-by-nc-sa-4.0
|
6 |
+
license_name: creative-commons
|
7 |
+
license_link: https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en
|
8 |
+
language:
|
9 |
+
- en
|
10 |
+
tags:
|
11 |
+
- text-generation
|
12 |
+
- artificial-intelligence
|
13 |
+
- not-for-all-audiences
|
14 |
---
|
15 |
+
|
16 |
+
## Valerie v0.1 Model Card
|
17 |
+
|
18 |
+
### Overview
|
19 |
+
|
20 |
+
Valerie v0.1 is a custom language model created using `llama.cpp` (commit: 532c173) with a context length of 256 tokens, embedding length of 256, 8 heads, and
|
21 |
+
16 layers. This model was pretrained on a dataset consisting of female V's dialog from Cyberpunk 2077, extracted using the [Voice Over Subtitle
|
22 |
+
Map](https://www.nexusmods.com/cyberpunk2077/mods/2045) mod.
|
23 |
+
|
24 |
+
The `ggml-valerie-v0.1-256x32-f32-LATEST.gguf` release represents a single pass through all 51443 samples, completing one iteration over the entire dataset,
|
25 |
+
and took approximately 3 hours for training.
|
26 |
+
|
27 |
+
### Model Information
|
28 |
+
|
29 |
+
| Model name | Adam iteration | Model filename |
|
30 |
+
| ----------------------- | -------------- | ---------------------------------------- |
|
31 |
+
| Valerie v0.1 Checkpoint | 950 | chk-valerie-v0.1-256x32-950.gguf |
|
32 |
+
| Valerie v0.1 Model | 1700 | ggml-valerie-v0.1-256x32-f32-LATEST.gguf |
|
33 |
+
|
34 |
+
### Files and versions
|
35 |
+
|
36 |
+
- ggml-valerie-v0.1-256x32-f32-950.gguf: The pretrained model checkpoint version 950.
|
37 |
+
- ggml-valerie-v0.1-256x32-f32-LATEST.gguf: The latest pretrained model checkpoint.
|
38 |
+
|
39 |
+
### Settings
|
40 |
+
|
41 |
+
- Context length: 256 tokens
|
42 |
+
- Embedding length: 256
|
43 |
+
- Heads: 8
|
44 |
+
- Layers: 16
|
45 |
+
- Batch size: 32
|
46 |
+
- Seed: 1
|
47 |
+
- Saved checkpoint every 50 iterations
|
48 |
+
|
49 |
+
### Usage
|
50 |
+
|
51 |
+
To use Valerie v0.1, follow these steps:
|
52 |
+
|
53 |
+
1. Install the required dependencies (e.g., GGML library).
|
54 |
+
|
55 |
+
```sh
|
56 |
+
git clone https://github.com/ggerganov/llama.cpp
|
57 |
+
```
|
58 |
+
|
59 |
+
Reference the `llama.cpp` README.md for more information.
|
60 |
+
|
61 |
+
2. Download or clone this repository.
|
62 |
+
|
63 |
+
```sh
|
64 |
+
wget https://huggingface.co/teleprint-me/cyberpunk/resolve/main/ggml-valerie-v0.1-256x32-f32-LATEST.gguf\?download\=true -O ggml-valerie-v0.1-256x32-f32-LATEST.gguf
|
65 |
+
```
|
66 |
+
|
67 |
+
This will download the latest available base model.
|
68 |
+
|
69 |
+
3. Perform inference with the latest model checkpoint using the provided command:
|
70 |
+
|
71 |
+
```sh
|
72 |
+
./main -m models/valerie/v0.1/ggml-valerie-v0.1-256x32-f32-LATEST.gguf --color -e -s 1 -c 4096
|
73 |
+
```
|
74 |
+
|
75 |
+
### Citing Valerie v0.1
|
76 |
+
|
77 |
+
When using Valerie v0.1 in your research, please remember to cite the following:
|
78 |
+
|
79 |
+
- Aberrio. (2023). Valerie v0.1: A custom language model for female V's dialog from Cyberpunk 2077. https://huggingface.co/teleprint-me/cyberpunk.
|
80 |
+
- julieisdead (2021). Voice Over Subtitle Map: Two files that contain the IDs for, Voice Over files the other Subtitles. https://www.nexusmods.com/cyberpunk2077/mods/2045
|
81 |
+
- GGML team. (2023). `llama.cpp` version `532c173`. Georgi Gerganov Machine Learning Library. https://github.com/ggerganov/llama.cpp
|
82 |
+
|
83 |
+
### Contributors
|
84 |
+
|
85 |
+
Austin Berrio (teleprint-me) - Created and trained Valerie v0.1 using `llama.cpp` and the referenced dataset.
|
86 |
+
|
87 |
+
### Community
|
88 |
+
|
89 |
+
Join the community of fellow language model enthusiasts and researchers by sharing your knowledge, asking questions, and collaborating on projects related to
|
90 |
+
creating custom models using `llama.cpp`.
|
91 |
+
|
92 |
+
### License
|
93 |
+
|
94 |
+
Valerie v0.1 is released under the CC-BY-NC-SA-3.0 license. You are free to use, modify, and redistribute this model for non-commercial purposes, but you must
|
95 |
+
provide attribution to the original authors and release any derived works under the same license.
|