Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -2,29 +2,49 @@
|
|
2 |
tags:
|
3 |
- llama-cpp
|
4 |
- gguf-my-repo
|
|
|
5 |
---
|
6 |
|
7 |
# 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF
|
8 |
This model was converted to GGUF format from [`2sy1227/gemma_2b_ko_summary`](https://huggingface.co/2sy1227/gemma_2b_ko_summary) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
9 |
Refer to the [original model card](https://huggingface.co/2sy1227/gemma_2b_ko_summary) for more details on the model.
|
|
|
10 |
## Use with llama.cpp
|
11 |
-
Install llama.cpp through brew
|
|
|
12 |
```bash
|
13 |
-
brew install
|
|
|
14 |
```
|
15 |
Invoke the llama.cpp server or the CLI.
|
16 |
-
|
|
|
17 |
```bash
|
18 |
-
llama
|
19 |
```
|
20 |
-
|
|
|
21 |
```bash
|
22 |
-
llama-server --hf-repo 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF --
|
23 |
```
|
|
|
24 |
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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
```
|
26 |
-
|
27 |
-
cd llama.cpp && \
|
28 |
-
make && \
|
29 |
-
./main -m gemma_2b_ko_summary-q4_k_m.gguf -n 128
|
30 |
```
|
|
|
2 |
tags:
|
3 |
- llama-cpp
|
4 |
- gguf-my-repo
|
5 |
+
base_model: 2sy1227/gemma_2b_ko_summary
|
6 |
---
|
7 |
|
8 |
# 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF
|
9 |
This model was converted to GGUF format from [`2sy1227/gemma_2b_ko_summary`](https://huggingface.co/2sy1227/gemma_2b_ko_summary) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
10 |
Refer to the [original model card](https://huggingface.co/2sy1227/gemma_2b_ko_summary) for more details on the model.
|
11 |
+
|
12 |
## Use with llama.cpp
|
13 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
14 |
+
|
15 |
```bash
|
16 |
+
brew install llama.cpp
|
17 |
+
|
18 |
```
|
19 |
Invoke the llama.cpp server or the CLI.
|
20 |
+
|
21 |
+
### CLI:
|
22 |
```bash
|
23 |
+
llama --hf-repo 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF --hf-file gemma_2b_ko_summary-q4_k_m.gguf -p "The meaning to life and the universe is"
|
24 |
```
|
25 |
+
|
26 |
+
### Server:
|
27 |
```bash
|
28 |
+
llama-server --hf-repo 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF --hf-file gemma_2b_ko_summary-q4_k_m.gguf -c 2048
|
29 |
```
|
30 |
+
|
31 |
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.
|
32 |
+
|
33 |
+
Step 1: Clone llama.cpp from GitHub.
|
34 |
+
```
|
35 |
+
git clone https://github.com/ggerganov/llama.cpp
|
36 |
+
```
|
37 |
+
|
38 |
+
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).
|
39 |
+
```
|
40 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
41 |
+
```
|
42 |
+
|
43 |
+
Step 3: Run inference through the main binary.
|
44 |
+
```
|
45 |
+
./main --hf-repo 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF --hf-file gemma_2b_ko_summary-q4_k_m.gguf -p "The meaning to life and the universe is"
|
46 |
+
```
|
47 |
+
or
|
48 |
```
|
49 |
+
./server --hf-repo 2sy1227/gemma_2b_ko_summary-Q4_K_M-GGUF --hf-file gemma_2b_ko_summary-q4_k_m.gguf -c 2048
|
|
|
|
|
|
|
50 |
```
|