Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -5,11 +5,11 @@ tags:
|
|
5 |
---
|
6 |
|
7 |
# reach-vb/gemma-1.1-2b-it-Q4_K_M-GGUF
|
8 |
-
This model was converted to GGUF format from [`gg-hf/gemma-1.1-2b-it`](https://huggingface.co/gg-hf/gemma-1.1-2b-it) using llama.cpp via the
|
9 |
Refer to the [original model card](https://huggingface.co/gg-hf/gemma-1.1-2b-it) for more details on the model.
|
10 |
## Use with llama.cpp
|
11 |
|
12 |
-
Install
|
13 |
|
14 |
```bash
|
15 |
brew install ggerganov/ggerganov/llama.cpp
|
@@ -19,7 +19,7 @@ Invoke the llama.cpp server or the CLI.
|
|
19 |
CLI:
|
20 |
|
21 |
```bash
|
22 |
-
llama-cli --hf-repo reach-vb/gemma-1.1-2b-it-Q4_K_M-GGUF --model gemma-1.1-2b-it.Q4_K_M.gguf -p "The meaning to life and the universe is
|
23 |
```
|
24 |
|
25 |
Server:
|
@@ -31,5 +31,5 @@ llama-server --hf-repo reach-vb/gemma-1.1-2b-it-Q4_K_M-GGUF --model gemma-1.1-2b
|
|
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 |
```
|
34 |
-
git clone https://github.com/ggerganov/llama.cpp &&
|
35 |
```
|
|
|
5 |
---
|
6 |
|
7 |
# reach-vb/gemma-1.1-2b-it-Q4_K_M-GGUF
|
8 |
+
This model was converted to GGUF format from [`gg-hf/gemma-1.1-2b-it`](https://huggingface.co/gg-hf/gemma-1.1-2b-it) 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/gg-hf/gemma-1.1-2b-it) for more details on the model.
|
10 |
## Use with llama.cpp
|
11 |
|
12 |
+
Install llama.cpp through brew.
|
13 |
|
14 |
```bash
|
15 |
brew install ggerganov/ggerganov/llama.cpp
|
|
|
19 |
CLI:
|
20 |
|
21 |
```bash
|
22 |
+
llama-cli --hf-repo reach-vb/gemma-1.1-2b-it-Q4_K_M-GGUF --model gemma-1.1-2b-it.Q4_K_M.gguf -p "The meaning to life and the universe is"
|
23 |
```
|
24 |
|
25 |
Server:
|
|
|
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 |
```
|
34 |
+
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m gemma-1.1-2b-it.Q4_K_M.gguf -n 128
|
35 |
```
|