Update README.md
Browse files
README.md
CHANGED
@@ -8,46 +8,21 @@ tags:
|
|
8 |
base_model: Nitral-AI/Hathor-L3-8B-v.01
|
9 |
---
|
10 |
|
11 |
-
|
12 |
-
|
13 |
-
Refer to the [original model card](https://huggingface.co/Nitral-AI/Hathor-L3-8B-v.01) for more details on the model.
|
14 |
|
15 |
-
|
16 |
-
Install llama.cpp through brew (works on Mac and Linux)
|
17 |
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
```
|
22 |
-
Invoke the llama.cpp server or the CLI.
|
23 |
-
|
24 |
-
### CLI:
|
25 |
-
```bash
|
26 |
-
llama --hf-repo Nitral-AI/Hathor-L3-8B-v.01-Q5_K_M-GGUF --hf-file hathor-l3-8b-v.01-q5_k_m.gguf -p "The meaning to life and the universe is"
|
27 |
-
```
|
28 |
-
|
29 |
-
### Server:
|
30 |
-
```bash
|
31 |
-
llama-server --hf-repo Nitral-AI/Hathor-L3-8B-v.01-Q5_K_M-GGUF --hf-file hathor-l3-8b-v.01-q5_k_m.gguf -c 2048
|
32 |
-
```
|
33 |
-
|
34 |
-
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
|
35 |
|
36 |
-
|
37 |
-
```
|
38 |
-
git clone https://github.com/ggerganov/llama.cpp
|
39 |
-
```
|
40 |
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
|
|
45 |
|
46 |
-
|
47 |
-
```
|
48 |
-
./main --hf-repo Nitral-AI/Hathor-L3-8B-v.01-Q5_K_M-GGUF --hf-file hathor-l3-8b-v.01-q5_k_m.gguf -p "The meaning to life and the universe is"
|
49 |
-
```
|
50 |
-
or
|
51 |
-
```
|
52 |
-
./server --hf-repo Nitral-AI/Hathor-L3-8B-v.01-Q5_K_M-GGUF --hf-file hathor-l3-8b-v.01-q5_k_m.gguf -c 2048
|
53 |
-
```
|
|
|
8 |
base_model: Nitral-AI/Hathor-L3-8B-v.01
|
9 |
---
|
10 |
|
11 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/kW6ij_aTIgOHvFKsqvidG.jpeg)
|
12 |
+
# "Hathor-v0.1 is a model based on the LLaMA 3 architecture: Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance. Making it an ideal tool for a wide range of applications; such as creative writing, educational support and human/computer interaction."
|
|
|
13 |
|
14 |
+
# Recomended ST Presets: [Hathor Presets](https://huggingface.co/Nitral-AI/Hathor-L3-8B-v.01/tree/main/Hathor%20Presets)
|
|
|
15 |
|
16 |
+
---
|
17 |
+
# Notes: Hathor is trained on 3 epochs of private rp data, synthetic opus instructons, a mix of light/classical novel data. (Heavily wip)
|
18 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
+
- If you want to use vision functionality:
|
|
|
|
|
|
|
21 |
|
22 |
+
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
|
23 |
+
|
24 |
+
- To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16)
|
25 |
+
|
26 |
+
* You can load the **mmproj** by using the corresponding section in the interface:
|
27 |
|
28 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
|
|
|
|
|
|
|
|
|
|
|
|
|
|