DavidAU commited on
Commit
a023401
1 Parent(s): d189d31

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +37 -0
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - llama-cpp
6
+ - gguf-my-repo
7
+ ---
8
+
9
+ # DavidAU/Configurable-Mistral-22B-Q6_K-GGUF
10
+ This model was converted to GGUF format from [`vicgalle/Configurable-Mistral-22B`](https://huggingface.co/vicgalle/Configurable-Mistral-22B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
11
+ Refer to the [original model card](https://huggingface.co/vicgalle/Configurable-Mistral-22B) for more details on the model.
12
+ ## Use with llama.cpp
13
+
14
+ Install llama.cpp through brew.
15
+
16
+ ```bash
17
+ brew install ggerganov/ggerganov/llama.cpp
18
+ ```
19
+ Invoke the llama.cpp server or the CLI.
20
+
21
+ CLI:
22
+
23
+ ```bash
24
+ llama-cli --hf-repo DavidAU/Configurable-Mistral-22B-Q6_K-GGUF --model configurable-mistral-22b.Q6_K.gguf -p "The meaning to life and the universe is"
25
+ ```
26
+
27
+ Server:
28
+
29
+ ```bash
30
+ llama-server --hf-repo DavidAU/Configurable-Mistral-22B-Q6_K-GGUF --model configurable-mistral-22b.Q6_K.gguf -c 2048
31
+ ```
32
+
33
+ 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.
34
+
35
+ ```
36
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m configurable-mistral-22b.Q6_K.gguf -n 128
37
+ ```