Sangto commited on
Commit
1a51e94
·
verified ·
1 Parent(s): c021e7c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - translation
5
+ - llama-cpp
6
+ - gguf-my-repo
7
+ license: gemma
8
+ language:
9
+ - ar
10
+ - bg
11
+ - zh
12
+ - cs
13
+ - da
14
+ - nl
15
+ - en
16
+ - fi
17
+ - fr
18
+ - de
19
+ - el
20
+ - gu
21
+ - he
22
+ - hi
23
+ - hu
24
+ - id
25
+ - it
26
+ - ja
27
+ - ko
28
+ - fa
29
+ - pl
30
+ - pt
31
+ - ro
32
+ - ru
33
+ - sk
34
+ - es
35
+ - sv
36
+ - tl
37
+ - th
38
+ - tr
39
+ - uk
40
+ - vi
41
+ base_model: yanolja/YanoljaNEXT-Rosetta-12B-2510
42
+ ---
43
+
44
+ # Sangto/YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF
45
+ This model was converted to GGUF format from [`yanolja/YanoljaNEXT-Rosetta-12B-2510`](https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-12B-2510) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
46
+ Refer to the [original model card](https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-12B-2510) for more details on the model.
47
+
48
+ ## Use with llama.cpp
49
+ Install llama.cpp through brew (works on Mac and Linux)
50
+
51
+ ```bash
52
+ brew install llama.cpp
53
+
54
+ ```
55
+ Invoke the llama.cpp server or the CLI.
56
+
57
+ ### CLI:
58
+ ```bash
59
+ llama-cli --hf-repo Sangto/YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF --hf-file yanoljanext-rosetta-12b-2510-q4_k_m.gguf -p "The meaning to life and the universe is"
60
+ ```
61
+
62
+ ### Server:
63
+ ```bash
64
+ llama-server --hf-repo Sangto/YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF --hf-file yanoljanext-rosetta-12b-2510-q4_k_m.gguf -c 2048
65
+ ```
66
+
67
+ 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.
68
+
69
+ Step 1: Clone llama.cpp from GitHub.
70
+ ```
71
+ git clone https://github.com/ggerganov/llama.cpp
72
+ ```
73
+
74
+ 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).
75
+ ```
76
+ cd llama.cpp && LLAMA_CURL=1 make
77
+ ```
78
+
79
+ Step 3: Run inference through the main binary.
80
+ ```
81
+ ./llama-cli --hf-repo Sangto/YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF --hf-file yanoljanext-rosetta-12b-2510-q4_k_m.gguf -p "The meaning to life and the universe is"
82
+ ```
83
+ or
84
+ ```
85
+ ./llama-server --hf-repo Sangto/YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF --hf-file yanoljanext-rosetta-12b-2510-q4_k_m.gguf -c 2048
86
+ ```