Hugging Face's logo

erenyeager-1
/
tiny-aya-water-Q4_K_S-GGUF

Transformers
GGUF
llama-cpp
gguf-my-repo
conversational
Model card Files
xet
 Community
erenyeager-1 commited on
Commit
db58b1f
·
verified ·
1 Parent(s): 67b9f1f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +131 -0
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - nl
7
+ - fr
8
+ - it
9
+ - pt
10
+ - ro
11
+ - es
12
+ - cs
13
+ - pl
14
+ - uk
15
+ - ru
16
+ - el
17
+ - de
18
+ - da
19
+ - sv
20
+ - 'no'
21
+ - ca
22
+ - gl
23
+ - cy
24
+ - ga
25
+ - eu
26
+ - hr
27
+ - lv
28
+ - lt
29
+ - sk
30
+ - sl
31
+ - et
32
+ - fi
33
+ - hu
34
+ - sr
35
+ - bg
36
+ - ar
37
+ - fa
38
+ - ur
39
+ - tr
40
+ - mt
41
+ - he
42
+ - hi
43
+ - mr
44
+ - bn
45
+ - gu
46
+ - pa
47
+ - ta
48
+ - te
49
+ - ne
50
+ - tl
51
+ - ms
52
+ - id
53
+ - vi
54
+ - jv
55
+ - km
56
+ - th
57
+ - lo
58
+ - zh
59
+ - my
60
+ - ja
61
+ - ko
62
+ - am
63
+ - ha
64
+ - ig
65
+ - mg
66
+ - sn
67
+ - sw
68
+ - wo
69
+ - xh
70
+ - yo
71
+ - zu
72
+ license: cc-by-nc-4.0
73
+ extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
74
+ acknowledge that the information you provide will be collected, used, and shared
75
+ in accordance with Cohere's [Privacy Policy]( https://cohere.com/privacy). You'll
76
+ receive email updates about Cohere Labs and Cohere research, events, products and
77
+ services. You can unsubscribe at any time.
78
+ extra_gated_fields:
79
+ Name: text
80
+ Affiliation: text
81
+ Country: country
82
+ I agree to use this model for non-commercial use ONLY: checkbox
83
+ base_model: CohereLabs/tiny-aya-water
84
+ tags:
85
+ - llama-cpp
86
+ - gguf-my-repo
87
+ ---
88
+
89
+ # erenyeager-1/tiny-aya-water-Q4_K_S-GGUF
90
+ This model was converted to GGUF format from [`CohereLabs/tiny-aya-water`](https://huggingface.co/CohereLabs/tiny-aya-water) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
91
+ Refer to the [original model card](https://huggingface.co/CohereLabs/tiny-aya-water) for more details on the model.
92
+
93
+ ## Use with llama.cpp
94
+ Install llama.cpp through brew (works on Mac and Linux)
95
+
96
+ ```bash
97
+ brew install llama.cpp
98
+
99
+ ```
100
+ Invoke the llama.cpp server or the CLI.
101
+
102
+ ### CLI:
103
+ ```bash
104
+ llama-cli --hf-repo erenyeager-1/tiny-aya-water-Q4_K_S-GGUF --hf-file tiny-aya-water-q4_k_s.gguf -p "The meaning to life and the universe is"
105
+ ```
106
+
107
+ ### Server:
108
+ ```bash
109
+ llama-server --hf-repo erenyeager-1/tiny-aya-water-Q4_K_S-GGUF --hf-file tiny-aya-water-q4_k_s.gguf -c 2048
110
+ ```
111
+
112
+ 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.
113
+
114
+ Step 1: Clone llama.cpp from GitHub.
115
+ ```
116
+ git clone https://github.com/ggerganov/llama.cpp
117
+ ```
118
+
119
+ 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).
120
+ ```
121
+ cd llama.cpp && LLAMA_CURL=1 make
122
+ ```
123
+
124
+ Step 3: Run inference through the main binary.
125
+ ```
126
+ ./llama-cli --hf-repo erenyeager-1/tiny-aya-water-Q4_K_S-GGUF --hf-file tiny-aya-water-q4_k_s.gguf -p "The meaning to life and the universe is"
127
+ ```
128
+ or
129
+ ```
130
+ ./llama-server --hf-repo erenyeager-1/tiny-aya-water-Q4_K_S-GGUF --hf-file tiny-aya-water-q4_k_s.gguf -c 2048
131
+ ```