qingy2024 commited on
Commit
36e55db
·
verified ·
1 Parent(s): 710fa7e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- base_model: qingy2024/UwU-7B-Instruct-ckpt-4000
3
  tags:
4
  - llama-cpp
5
  - gguf-my-repo
6
  ---
7
 
8
- # qingy2024/UwU-7B-Instruct-ckpt-4000-Q5_K_M-GGUF
9
- This model was converted to GGUF format from [`qingy2024/UwU-7B-Instruct-ckpt-4000`](https://huggingface.co/qingy2024/UwU-7B-Instruct-ckpt-4000) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
10
- Refer to the [original model card](https://huggingface.co/qingy2024/UwU-7B-Instruct-ckpt-4000) for more details on the model.
11
 
12
  ## Use with llama.cpp
13
  Install llama.cpp through brew (works on Mac and Linux)
@@ -20,12 +20,12 @@ Invoke the llama.cpp server or the CLI.
20
 
21
  ### CLI:
22
  ```bash
23
- llama-cli --hf-repo qingy2024/UwU-7B-Instruct-ckpt-4000-Q5_K_M-GGUF --hf-file uwu-7b-instruct-ckpt-4000-q5_k_m.gguf -p "The meaning to life and the universe is"
24
  ```
25
 
26
  ### Server:
27
  ```bash
28
- llama-server --hf-repo qingy2024/UwU-7B-Instruct-ckpt-4000-Q5_K_M-GGUF --hf-file uwu-7b-instruct-ckpt-4000-q5_k_m.gguf -c 2048
29
  ```
30
 
31
  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.
@@ -42,9 +42,9 @@ cd llama.cpp && LLAMA_CURL=1 make
42
 
43
  Step 3: Run inference through the main binary.
44
  ```
45
- ./llama-cli --hf-repo qingy2024/UwU-7B-Instruct-ckpt-4000-Q5_K_M-GGUF --hf-file uwu-7b-instruct-ckpt-4000-q5_k_m.gguf -p "The meaning to life and the universe is"
46
  ```
47
  or
48
  ```
49
- ./llama-server --hf-repo qingy2024/UwU-7B-Instruct-ckpt-4000-Q5_K_M-GGUF --hf-file uwu-7b-instruct-ckpt-4000-q5_k_m.gguf -c 2048
50
  ```
 
1
  ---
2
+ base_model: qingy2024/UwU-7B-Instruct
3
  tags:
4
  - llama-cpp
5
  - gguf-my-repo
6
  ---
7
 
8
+ # qingy2024/UwU-7B-Instruct-GGUF
9
+ This model was converted to GGUF format from [`qingy2024/UwU-7B-Instruct`](https://huggingface.co/qingy2024/UwU-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
10
+ Refer to the [original model card](https://huggingface.co/qingy2024/UwU-7B-Instruct) for more details on the model.
11
 
12
  ## Use with llama.cpp
13
  Install llama.cpp through brew (works on Mac and Linux)
 
20
 
21
  ### CLI:
22
  ```bash
23
+ llama-cli --hf-repo qingy2024/UwU-7B-Instruct-Q5_K_M-GGUF --hf-file uwu-7b-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
24
  ```
25
 
26
  ### Server:
27
  ```bash
28
+ llama-server --hf-repo qingy2024/UwU-7B-Instruct-Q5_K_M-GGUF --hf-file uwu-7b-instruct-q5_k_m.gguf -c 2048
29
  ```
30
 
31
  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.
 
42
 
43
  Step 3: Run inference through the main binary.
44
  ```
45
+ ./llama-cli --hf-repo qingy2024/UwU-7B-Instruct-Q5_K_M-GGUF --hf-file uwu-7b-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
46
  ```
47
  or
48
  ```
49
+ ./llama-server --hf-repo qingy2024/UwU-7B-Instruct-Q5_K_M-GGUF --hf-file uwu-7b-instruct-q5_k_m.gguf -c 2048
50
  ```