Cran-May commited on
Commit
8f6581d
1 Parent(s): 4812051

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ghost-x/ghost-8b-beta-1608
3
+ language:
4
+ - vi
5
+ - ko
6
+ - es
7
+ - pt
8
+ - zh
9
+ - fr
10
+ - it
11
+ - de
12
+ - ja
13
+ - ru
14
+ - pl
15
+ - nl
16
+ - hi
17
+ - tr
18
+ - id
19
+ - en
20
+ license: other
21
+ license_name: ghost-open-llms
22
+ license_link: https://ghost-x.org/ghost-open-llms-license
23
+ pipeline_tag: text-generation
24
+ tags:
25
+ - ghost
26
+ - tools
27
+ - chat
28
+ - transformers
29
+ - unsloth
30
+ - llama
31
+ - llama-cpp
32
+ - gguf-my-repo
33
+ widget:
34
+ - text: Why is the sky blue ?
35
+ ---
36
+
37
+ # Cran-May/ghost-8b-beta-1608-Q4_K_M-GGUF
38
+ This model was converted to GGUF format from [`ghost-x/ghost-8b-beta-1608`](https://huggingface.co/ghost-x/ghost-8b-beta-1608) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
39
+ Refer to the [original model card](https://huggingface.co/ghost-x/ghost-8b-beta-1608) for more details on the model.
40
+
41
+ ## Use with llama.cpp
42
+ Install llama.cpp through brew (works on Mac and Linux)
43
+
44
+ ```bash
45
+ brew install llama.cpp
46
+
47
+ ```
48
+ Invoke the llama.cpp server or the CLI.
49
+
50
+ ### CLI:
51
+ ```bash
52
+ llama-cli --hf-repo Cran-May/ghost-8b-beta-1608-Q4_K_M-GGUF --hf-file ghost-8b-beta-1608-q4_k_m-imat.gguf -p "The meaning to life and the universe is"
53
+ ```
54
+
55
+ ### Server:
56
+ ```bash
57
+ llama-server --hf-repo Cran-May/ghost-8b-beta-1608-Q4_K_M-GGUF --hf-file ghost-8b-beta-1608-q4_k_m-imat.gguf -c 2048
58
+ ```
59
+
60
+ 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.
61
+
62
+ Step 1: Clone llama.cpp from GitHub.
63
+ ```
64
+ git clone https://github.com/ggerganov/llama.cpp
65
+ ```
66
+
67
+ 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).
68
+ ```
69
+ cd llama.cpp && LLAMA_CURL=1 make
70
+ ```
71
+
72
+ Step 3: Run inference through the main binary.
73
+ ```
74
+ ./llama-cli --hf-repo Cran-May/ghost-8b-beta-1608-Q4_K_M-GGUF --hf-file ghost-8b-beta-1608-q4_k_m-imat.gguf -p "The meaning to life and the universe is"
75
+ ```
76
+ or
77
+ ```
78
+ ./llama-server --hf-repo Cran-May/ghost-8b-beta-1608-Q4_K_M-GGUF --hf-file ghost-8b-beta-1608-q4_k_m-imat.gguf -c 2048
79
+ ```