Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: gemma
|
3 |
+
license_name: license
|
4 |
+
license_link: LICENSE
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
- comet
|
8 |
+
base_model: ModelSpace/GemmaX2-28-2B-v0.1
|
9 |
+
pipeline_tag: translation
|
10 |
+
library_name: transformers
|
11 |
+
language:
|
12 |
+
- ar
|
13 |
+
- bn
|
14 |
+
- cs
|
15 |
+
- de
|
16 |
+
- en
|
17 |
+
- es
|
18 |
+
- fa
|
19 |
+
- fr
|
20 |
+
- he
|
21 |
+
- hi
|
22 |
+
- id
|
23 |
+
- it
|
24 |
+
- ja
|
25 |
+
- km
|
26 |
+
- ko
|
27 |
+
- lo
|
28 |
+
- ms
|
29 |
+
- my
|
30 |
+
- nl
|
31 |
+
- pl
|
32 |
+
- pt
|
33 |
+
- ru
|
34 |
+
- th
|
35 |
+
- tl
|
36 |
+
- tr
|
37 |
+
- ur
|
38 |
+
- vi
|
39 |
+
- zh
|
40 |
+
tags:
|
41 |
+
- llama-cpp
|
42 |
+
- gguf-my-repo
|
43 |
+
---
|
44 |
+
|
45 |
+
# N19hty/GemmaX2-28-2B-v0.1-IQ3_XXS-GGUF
|
46 |
+
This model was converted to GGUF format from [`ModelSpace/GemmaX2-28-2B-v0.1`](https://huggingface.co/ModelSpace/GemmaX2-28-2B-v0.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
47 |
+
Refer to the [original model card](https://huggingface.co/ModelSpace/GemmaX2-28-2B-v0.1) for more details on the model.
|
48 |
+
|
49 |
+
## Use with llama.cpp
|
50 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
51 |
+
|
52 |
+
```bash
|
53 |
+
brew install llama.cpp
|
54 |
+
|
55 |
+
```
|
56 |
+
Invoke the llama.cpp server or the CLI.
|
57 |
+
|
58 |
+
### CLI:
|
59 |
+
```bash
|
60 |
+
llama-cli --hf-repo N19hty/GemmaX2-28-2B-v0.1-IQ3_XXS-GGUF --hf-file gemmax2-28-2b-v0.1-iq3_xxs-imat.gguf -p "The meaning to life and the universe is"
|
61 |
+
```
|
62 |
+
|
63 |
+
### Server:
|
64 |
+
```bash
|
65 |
+
llama-server --hf-repo N19hty/GemmaX2-28-2B-v0.1-IQ3_XXS-GGUF --hf-file gemmax2-28-2b-v0.1-iq3_xxs-imat.gguf -c 2048
|
66 |
+
```
|
67 |
+
|
68 |
+
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.
|
69 |
+
|
70 |
+
Step 1: Clone llama.cpp from GitHub.
|
71 |
+
```
|
72 |
+
git clone https://github.com/ggerganov/llama.cpp
|
73 |
+
```
|
74 |
+
|
75 |
+
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
|
76 |
+
```
|
77 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
78 |
+
```
|
79 |
+
|
80 |
+
Step 3: Run inference through the main binary.
|
81 |
+
```
|
82 |
+
./llama-cli --hf-repo N19hty/GemmaX2-28-2B-v0.1-IQ3_XXS-GGUF --hf-file gemmax2-28-2b-v0.1-iq3_xxs-imat.gguf -p "The meaning to life and the universe is"
|
83 |
+
```
|
84 |
+
or
|
85 |
+
```
|
86 |
+
./llama-server --hf-repo N19hty/GemmaX2-28-2B-v0.1-IQ3_XXS-GGUF --hf-file gemmax2-28-2b-v0.1-iq3_xxs-imat.gguf -c 2048
|
87 |
+
```
|