matrixportal commited on
Commit
05a1ec3
·
verified ·
1 Parent(s): 24b9b20

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
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ - ja
12
+ - ko
13
+ - zh
14
+ - ar
15
+ - el
16
+ - fa
17
+ - pl
18
+ - id
19
+ - cs
20
+ - he
21
+ - hi
22
+ - nl
23
+ - ro
24
+ - ru
25
+ - tr
26
+ - uk
27
+ - vi
28
+ license: cc-by-nc-4.0
29
+ base_model: lenML/aya-expanse-8b-abliterated
30
+ tags:
31
+ - gguf
32
+ - CohereForAI
33
+ - llama-cpp
34
+ - gguf-my-repo
35
+ ---
36
+
37
+ # matrixportal/aya-expanse-8b-abliterated-Q4_K_S-GGUF
38
+ This model was converted to GGUF format from [`lenML/aya-expanse-8b-abliterated`](https://huggingface.co/lenML/aya-expanse-8b-abliterated) 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/lenML/aya-expanse-8b-abliterated) 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 matrixportal/aya-expanse-8b-abliterated-Q4_K_S-GGUF --hf-file aya-expanse-8b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
53
+ ```
54
+
55
+ ### Server:
56
+ ```bash
57
+ llama-server --hf-repo matrixportal/aya-expanse-8b-abliterated-Q4_K_S-GGUF --hf-file aya-expanse-8b-abliterated-q4_k_s.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 matrixportal/aya-expanse-8b-abliterated-Q4_K_S-GGUF --hf-file aya-expanse-8b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
75
+ ```
76
+ or
77
+ ```
78
+ ./llama-server --hf-repo matrixportal/aya-expanse-8b-abliterated-Q4_K_S-GGUF --hf-file aya-expanse-8b-abliterated-q4_k_s.gguf -c 2048
79
+ ```