Update README.md
Browse files
README.md
CHANGED
@@ -3,52 +3,80 @@ library_name: transformers
|
|
3 |
tags:
|
4 |
- mergekit
|
5 |
- merge
|
6 |
-
- not-for-all-audiences
|
7 |
- llama-cpp
|
8 |
- gguf-my-repo
|
9 |
-
|
|
|
|
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
# v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF
|
13 |
This model was converted to GGUF format from [`v000000/MysticGem-v1.3-L2-13B`](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
14 |
Refer to the [original model card](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) for more details on the model.
|
15 |
|
16 |
-
|
17 |
-
Install llama.cpp through brew (works on Mac and Linux)
|
18 |
|
19 |
-
|
20 |
-
brew install llama.cpp
|
21 |
|
22 |
-
|
23 |
-
|
24 |
|
25 |
-
|
26 |
-
```bash
|
27 |
-
llama --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -p "The meaning to life and the universe is"
|
28 |
-
```
|
29 |
|
30 |
-
###
|
31 |
-
```bash
|
32 |
-
llama-server --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -c 2048
|
33 |
-
```
|
34 |
|
35 |
-
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
-
|
38 |
-
```
|
39 |
-
git clone https://github.com/ggerganov/llama.cpp
|
40 |
-
```
|
41 |
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
-
Step 3: Run inference through the main binary.
|
48 |
-
```
|
49 |
-
./main --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -p "The meaning to life and the universe is"
|
50 |
-
```
|
51 |
-
or
|
52 |
```
|
53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
```
|
|
|
3 |
tags:
|
4 |
- mergekit
|
5 |
- merge
|
|
|
6 |
- llama-cpp
|
7 |
- gguf-my-repo
|
8 |
+
- not-for-all-audiences
|
9 |
+
- llama
|
10 |
+
base_model: v000000/l2-test-001
|
11 |
---
|
12 |
|
13 |
+
# MysticGem-v1.3-L2-13B l2-test-001
|
14 |
+
|
15 |
+
RP Model, pretty good result!
|
16 |
+
|
17 |
+
Probably final. Smart, novel, lewd etc etc.
|
18 |
+
|
19 |
+
### Rank no.1 chaiverse for 13B
|
20 |
+
|
21 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/lKzERgJPnOxxzWsGJ-86M.png)
|
22 |
+
|
23 |
# v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF
|
24 |
This model was converted to GGUF format from [`v000000/MysticGem-v1.3-L2-13B`](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
25 |
Refer to the [original model card](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) for more details on the model.
|
26 |
|
27 |
+
# merge
|
|
|
28 |
|
29 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
30 |
|
31 |
+
## Merge Details
|
32 |
+
### Merge Method
|
33 |
|
34 |
+
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
|
|
|
|
|
|
35 |
|
36 |
+
### Models Merged
|
|
|
|
|
|
|
37 |
|
38 |
+
The following models were included in the merge:
|
39 |
+
* [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3)
|
40 |
+
* [Locutusque/Orca-2-13b-SFT-v4](https://huggingface.co/Locutusque/Orca-2-13b-SFT-v4)
|
41 |
+
* [Sao10K/Stheno-Inverted-1.2-L2-13B](https://huggingface.co/Sao10K/Stheno-Inverted-1.2-L2-13B)
|
42 |
+
* [Walmart-the-bag/MysticFusion-13B](https://huggingface.co/Walmart-the-bag/MysticFusion-13B)
|
43 |
+
* [Undi95/Amethyst-13B](https://huggingface.co/Undi95/Amethyst-13B)
|
44 |
|
45 |
+
### Configuration
|
|
|
|
|
|
|
46 |
|
47 |
+
The following YAML configuration was used to produce this model:
|
48 |
+
|
49 |
+
```yaml
|
50 |
+
models:
|
51 |
+
- model: Undi95/Amethyst-13B
|
52 |
+
parameters:
|
53 |
+
weight: 0.3
|
54 |
+
- model: Walmart-the-bag/MysticFusion-13B
|
55 |
+
parameters:
|
56 |
+
weight: 0.35
|
57 |
+
- model: Sao10K/Stheno-Inverted-1.2-L2-13B
|
58 |
+
parameters:
|
59 |
+
weight: 0.15
|
60 |
+
- model: KoboldAI/LLaMA2-13B-Erebus-v3
|
61 |
+
parameters:
|
62 |
+
weight: 0.1
|
63 |
+
- model: Locutusque/Orca-2-13b-SFT-v4
|
64 |
+
parameters:
|
65 |
+
weight: 0.1
|
66 |
+
merge_method: linear
|
67 |
+
dtype: bfloat16
|
68 |
|
|
|
|
|
|
|
|
|
|
|
69 |
```
|
70 |
+
|
71 |
+
### Prompt Format (Alpaca):
|
72 |
+
```bash
|
73 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
74 |
+
|
75 |
+
### Instruction:
|
76 |
+
Take the role of {{char}} in a play where you leave a lasting impression on {{user}}. Never skip or gloss over {{char}}'s actions.
|
77 |
+
|
78 |
+
### Instruction:
|
79 |
+
{prompt}
|
80 |
+
### Response:
|
81 |
+
{output}
|
82 |
```
|