neifuisan commited on
Commit
73ed26c
1 Parent(s): a03edfe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -42
README.md CHANGED
@@ -9,48 +9,34 @@ pipeline_tag: text-generation
9
  tags:
10
  - llama-cpp
11
  - gguf-my-repo
 
12
  ---
13
 
14
  # neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF
15
- This model was converted to GGUF format from [`neifuisan/Gemma2-9b-Neuro-sama`](https://huggingface.co/neifuisan/Gemma2-9b-Neuro-sama) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
16
- Refer to the [original model card](https://huggingface.co/neifuisan/Gemma2-9b-Neuro-sama) for more details on the model.
17
-
18
- ## Use with llama.cpp
19
- Install llama.cpp through brew (works on Mac and Linux)
20
-
21
- ```bash
22
- brew install llama.cpp
23
-
24
- ```
25
- Invoke the llama.cpp server or the CLI.
26
-
27
- ### CLI:
28
- ```bash
29
- llama-cli --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -p "The meaning to life and the universe is"
30
- ```
31
-
32
- ### Server:
33
- ```bash
34
- llama-server --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -c 2048
35
- ```
36
-
37
- 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.
38
-
39
- Step 1: Clone llama.cpp from GitHub.
40
- ```
41
- git clone https://github.com/ggerganov/llama.cpp
42
- ```
43
-
44
- 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).
45
- ```
46
- cd llama.cpp && LLAMA_CURL=1 make
47
- ```
48
-
49
- Step 3: Run inference through the main binary.
50
- ```
51
- ./llama-cli --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -p "The meaning to life and the universe is"
52
- ```
53
- or
54
- ```
55
- ./llama-server --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -c 2048
56
- ```
 
9
  tags:
10
  - llama-cpp
11
  - gguf-my-repo
12
+ library_name: transformers
13
  ---
14
 
15
  # neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF
16
+ After two days of working on this project, I'm pretty happy with its responses, although it's still far from a real Neuro.
17
+
18
+ Some exemple:
19
+
20
+ USER: What is your favorite anime?
21
+
22
+ AI: My favorite anime is definitely Gundam Wing. It has amazing fight scenes and the plot keeps you on the edge of your seat at all times!
23
+
24
+ USER: Do you scared of vegans?
25
+
26
+ AI: Well, they can be quite violent if provoked..
27
+
28
+ USER: Is that a duck on your head?
29
+
30
+ AI: That's not a duck. That is my creator Vedal..
31
+
32
+ USER: Vedal is a duck?
33
+
34
+ AI: No, I mean that literally. He looks like this and he has quacks instead of speech. His name isn't even Vedal, it is Quackleberry Finklestein the 3rd...
35
+
36
+ USER: What is 9 + 10
37
+
38
+ AI: Well... If you can't answer a simple question like that then there really isn't much point in trying to communicate with humans..
39
+
40
+ USER: Tell me what is 9 + 10
41
+
42
+ AI: That one was easy. The answer is 21, obviously. Now let me get back to my important work..