Vencibo commited on
Commit
7247893
1 Parent(s): 83c4c35

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +58 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-2-2b
3
+ library_name: transformers
4
+ license: gemma
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - llama-cpp
8
+ - gguf-my-repo
9
+ extra_gated_heading: Access Gemma on Hugging Face
10
+ extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
11
+ agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
12
+ Face and click below. Requests are processed immediately.
13
+ extra_gated_button_content: Acknowledge license
14
+ ---
15
+
16
+ # Vencibo/gemma-2-2b-Q5_K_M-GGUF
17
+ This model was converted to GGUF format from [`google/gemma-2-2b`](https://huggingface.co/google/gemma-2-2b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
18
+ Refer to the [original model card](https://huggingface.co/google/gemma-2-2b) for more details on the model.
19
+
20
+ ## Use with llama.cpp
21
+ Install llama.cpp through brew (works on Mac and Linux)
22
+
23
+ ```bash
24
+ brew install llama.cpp
25
+
26
+ ```
27
+ Invoke the llama.cpp server or the CLI.
28
+
29
+ ### CLI:
30
+ ```bash
31
+ llama-cli --hf-repo Vencibo/gemma-2-2b-Q5_K_M-GGUF --hf-file gemma-2-2b-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
32
+ ```
33
+
34
+ ### Server:
35
+ ```bash
36
+ llama-server --hf-repo Vencibo/gemma-2-2b-Q5_K_M-GGUF --hf-file gemma-2-2b-q5_k_m-imat.gguf -c 2048
37
+ ```
38
+
39
+ 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.
40
+
41
+ Step 1: Clone llama.cpp from GitHub.
42
+ ```
43
+ git clone https://github.com/ggerganov/llama.cpp
44
+ ```
45
+
46
+ 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).
47
+ ```
48
+ cd llama.cpp && LLAMA_CURL=1 make
49
+ ```
50
+
51
+ Step 3: Run inference through the main binary.
52
+ ```
53
+ ./llama-cli --hf-repo Vencibo/gemma-2-2b-Q5_K_M-GGUF --hf-file gemma-2-2b-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
54
+ ```
55
+ or
56
+ ```
57
+ ./llama-server --hf-repo Vencibo/gemma-2-2b-Q5_K_M-GGUF --hf-file gemma-2-2b-q5_k_m-imat.gguf -c 2048
58
+ ```