Skier8402 commited on
Commit
3c78715
·
verified ·
1 Parent(s): eb7da10

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - sw
5
+ base_model: Alfaxad/gemma2-2b-swahili-it
6
+ pipeline_tag: text-generation
7
+ library_name: transformers
8
+ tags:
9
+ - swahili
10
+ - gemma2
11
+ - text-generation-inference
12
+ - text-generation
13
+ - llama-cpp
14
+ - gguf-my-repo
15
+ inference:
16
+ parameters:
17
+ temperature: 0.7
18
+ top_p: 0.95
19
+ max_new_tokens: 500
20
+ do_sample: true
21
+ eval_mode: true
22
+ model_kwargs:
23
+ eval_mode: true
24
+ ---
25
+
26
+ # Skier8402/gemma2-2b-swahili-it-Q4_K_M-GGUF
27
+ This model was converted to GGUF format from [`Alfaxad/gemma2-2b-swahili-it`](https://huggingface.co/Alfaxad/gemma2-2b-swahili-it) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
28
+ Refer to the [original model card](https://huggingface.co/Alfaxad/gemma2-2b-swahili-it) for more details on the model.
29
+
30
+ ## Use with llama.cpp
31
+ Install llama.cpp through brew (works on Mac and Linux)
32
+
33
+ ```bash
34
+ brew install llama.cpp
35
+
36
+ ```
37
+ Invoke the llama.cpp server or the CLI.
38
+
39
+ ### CLI:
40
+ ```bash
41
+ llama-cli --hf-repo Skier8402/gemma2-2b-swahili-it-Q4_K_M-GGUF --hf-file gemma2-2b-swahili-it-q4_k_m.gguf -p "The meaning to life and the universe is"
42
+ ```
43
+
44
+ ### Server:
45
+ ```bash
46
+ llama-server --hf-repo Skier8402/gemma2-2b-swahili-it-Q4_K_M-GGUF --hf-file gemma2-2b-swahili-it-q4_k_m.gguf -c 2048
47
+ ```
48
+
49
+ 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.
50
+
51
+ Step 1: Clone llama.cpp from GitHub.
52
+ ```
53
+ git clone https://github.com/ggerganov/llama.cpp
54
+ ```
55
+
56
+ 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).
57
+ ```
58
+ cd llama.cpp && LLAMA_CURL=1 make
59
+ ```
60
+
61
+ Step 3: Run inference through the main binary.
62
+ ```
63
+ ./llama-cli --hf-repo Skier8402/gemma2-2b-swahili-it-Q4_K_M-GGUF --hf-file gemma2-2b-swahili-it-q4_k_m.gguf -p "The meaning to life and the universe is"
64
+ ```
65
+ or
66
+ ```
67
+ ./llama-server --hf-repo Skier8402/gemma2-2b-swahili-it-Q4_K_M-GGUF --hf-file gemma2-2b-swahili-it-q4_k_m.gguf -c 2048
68
+ ```