HawkClaws commited on
Commit
2fc9d93
1 Parent(s): 6223d86

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - llama-cpp
4
+ - gguf-my-repo
5
+ ---
6
+
7
+ # HawkClaws/Raven-JP-7B-Q8_0-GGUF
8
+ This model was converted to GGUF format from [`HawkClaws/Raven-JP-7B`](https://huggingface.co/HawkClaws/Raven-JP-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
9
+ Refer to the [original model card](https://huggingface.co/HawkClaws/Raven-JP-7B) for more details on the model.
10
+ ## Use with llama.cpp
11
+ Install llama.cpp through brew.
12
+ ```bash
13
+ brew install ggerganov/ggerganov/llama.cpp
14
+ ```
15
+ Invoke the llama.cpp server or the CLI.
16
+ CLI:
17
+ ```bash
18
+ llama-cli --hf-repo HawkClaws/Raven-JP-7B-Q8_0-GGUF --model raven-jp-7b-q8_0.gguf -p "The meaning to life and the universe is"
19
+ ```
20
+ Server:
21
+ ```bash
22
+ llama-server --hf-repo HawkClaws/Raven-JP-7B-Q8_0-GGUF --model raven-jp-7b-q8_0.gguf -c 2048
23
+ ```
24
+ 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.
25
+ ```
26
+ git clone https://github.com/ggerganov/llama.cpp && \
27
+ cd llama.cpp && \
28
+ make && \
29
+ ./main -m raven-jp-7b-q8_0.gguf -n 128
30
+ ```