Sangto commited on
Commit
d5b5634
1 Parent(s): 3b6190d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
3
+ language:
4
+ - en
5
+ - de
6
+ - fr
7
+ - it
8
+ - pt
9
+ - hi
10
+ - es
11
+ - th
12
+ - zh
13
+ - ko
14
+ - ja
15
+ license: llama3.1
16
+ pipeline_tag: text-generation
17
+ tags:
18
+ - roleplay
19
+ - llama3
20
+ - sillytavern
21
+ - idol
22
+ - facebook
23
+ - meta
24
+ - pytorch
25
+ - llama
26
+ - llama-3
27
+ - llama-cpp
28
+ - gguf-my-repo
29
+ extra_gated_fields:
30
+ First Name: text
31
+ Last Name: text
32
+ Date of birth: date_picker
33
+ Country: country
34
+ Affiliation: text
35
+ Job title:
36
+ type: select
37
+ options:
38
+ - Student
39
+ - Research Graduate
40
+ - AI researcher
41
+ - AI developer/engineer
42
+ - Reporter
43
+ - Other
44
+ ---
45
+
46
+ # Sangto/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0-GGUF
47
+ This model was converted to GGUF format from [`aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored`](https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
48
+ Refer to the [original model card](https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored) for more details on the model.
49
+
50
+ ## Use with llama.cpp
51
+ Install llama.cpp through brew (works on Mac and Linux)
52
+
53
+ ```bash
54
+ brew install llama.cpp
55
+
56
+ ```
57
+ Invoke the llama.cpp server or the CLI.
58
+
59
+ ### CLI:
60
+ ```bash
61
+ llama-cli --hf-repo Sangto/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0-GGUF --hf-file darkidol-llama-3.1-8b-instruct-1.2-uncensored-q8_0.gguf -p "The meaning to life and the universe is"
62
+ ```
63
+
64
+ ### Server:
65
+ ```bash
66
+ llama-server --hf-repo Sangto/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0-GGUF --hf-file darkidol-llama-3.1-8b-instruct-1.2-uncensored-q8_0.gguf -c 2048
67
+ ```
68
+
69
+ 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.
70
+
71
+ Step 1: Clone llama.cpp from GitHub.
72
+ ```
73
+ git clone https://github.com/ggerganov/llama.cpp
74
+ ```
75
+
76
+ 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).
77
+ ```
78
+ cd llama.cpp && LLAMA_CURL=1 make
79
+ ```
80
+
81
+ Step 3: Run inference through the main binary.
82
+ ```
83
+ ./llama-cli --hf-repo Sangto/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0-GGUF --hf-file darkidol-llama-3.1-8b-instruct-1.2-uncensored-q8_0.gguf -p "The meaning to life and the universe is"
84
+ ```
85
+ or
86
+ ```
87
+ ./llama-server --hf-repo Sangto/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0-GGUF --hf-file darkidol-llama-3.1-8b-instruct-1.2-uncensored-q8_0.gguf -c 2048
88
+ ```