AIronMind commited on
Commit
0849a80
1 Parent(s): e662501

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - zh
5
+ - id
6
+ - th
7
+ - vi
8
+ - ms
9
+ - lo
10
+ - my
11
+ - jv
12
+ - km
13
+ - su
14
+ - tl
15
+ tags:
16
+ - multilingual
17
+ - sea
18
+ - sailor
19
+ - sft
20
+ - chat
21
+ - instruction
22
+ - llama-cpp
23
+ - gguf-my-repo
24
+ widget:
25
+ - text: 如何制作烤鱼?
26
+ example_title: Chinese
27
+ - text: How to bake fish?
28
+ example_title: English
29
+ - text: Bagaimana cara memanggang ikan?
30
+ example_title: Malay
31
+ - text: วิธีย่างปลา?
32
+ example_title: Thai
33
+ - text: Bagaimana membuat bakaran ikan?
34
+ example_title: Indonesian
35
+ - text: Làm thế nào để nướng cá?
36
+ example_title: Vietnamese
37
+ license: apache-2.0
38
+ base_model: sail/Sailor2-20B
39
+ ---
40
+
41
+ # AIronMind/Sailor2-20B-Q4_K_M-GGUF
42
+ This model was converted to GGUF format from [`sail/Sailor2-20B`](https://huggingface.co/sail/Sailor2-20B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
43
+ Refer to the [original model card](https://huggingface.co/sail/Sailor2-20B) for more details on the model.
44
+
45
+ ## Use with llama.cpp
46
+ Install llama.cpp through brew (works on Mac and Linux)
47
+
48
+ ```bash
49
+ brew install llama.cpp
50
+
51
+ ```
52
+ Invoke the llama.cpp server or the CLI.
53
+
54
+ ### CLI:
55
+ ```bash
56
+ llama-cli --hf-repo AIronMind/Sailor2-20B-Q4_K_M-GGUF --hf-file sailor2-20b-q4_k_m.gguf -p "The meaning to life and the universe is"
57
+ ```
58
+
59
+ ### Server:
60
+ ```bash
61
+ llama-server --hf-repo AIronMind/Sailor2-20B-Q4_K_M-GGUF --hf-file sailor2-20b-q4_k_m.gguf -c 2048
62
+ ```
63
+
64
+ 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.
65
+
66
+ Step 1: Clone llama.cpp from GitHub.
67
+ ```
68
+ git clone https://github.com/ggerganov/llama.cpp
69
+ ```
70
+
71
+ 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).
72
+ ```
73
+ cd llama.cpp && LLAMA_CURL=1 make
74
+ ```
75
+
76
+ Step 3: Run inference through the main binary.
77
+ ```
78
+ ./llama-cli --hf-repo AIronMind/Sailor2-20B-Q4_K_M-GGUF --hf-file sailor2-20b-q4_k_m.gguf -p "The meaning to life and the universe is"
79
+ ```
80
+ or
81
+ ```
82
+ ./llama-server --hf-repo AIronMind/Sailor2-20B-Q4_K_M-GGUF --hf-file sailor2-20b-q4_k_m.gguf -c 2048
83
+ ```