HDiffusion commited on
Commit
e718f23
1 Parent(s): 16f644c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +57 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ library_name: transformers
4
+ tags:
5
+ - unsloth
6
+ - trl
7
+ - sft
8
+ - llama-cpp
9
+ - gguf-my-repo
10
+ base_model: SchizoDev/Llama3-8b-CunnyGPT-16bit
11
+ datasets:
12
+ - SchizoDev/CunnyGPT
13
+ ---
14
+
15
+ # HDiffusion/Llama3-8b-CunnyGPT-16bit-Q4_K_M-GGUF
16
+ This model was converted to GGUF format from [`SchizoDev/Llama3-8b-CunnyGPT-16bit`](https://huggingface.co/SchizoDev/Llama3-8b-CunnyGPT-16bit) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
17
+ Refer to the [original model card](https://huggingface.co/SchizoDev/Llama3-8b-CunnyGPT-16bit) for more details on the model.
18
+
19
+ ## Use with llama.cpp
20
+ Install llama.cpp through brew (works on Mac and Linux)
21
+
22
+ ```bash
23
+ brew install llama.cpp
24
+
25
+ ```
26
+ Invoke the llama.cpp server or the CLI.
27
+
28
+ ### CLI:
29
+ ```bash
30
+ llama --hf-repo HDiffusion/Llama3-8b-CunnyGPT-16bit-Q4_K_M-GGUF --hf-file llama3-8b-cunnygpt-16bit-q4_k_m.gguf -p "The meaning to life and the universe is"
31
+ ```
32
+
33
+ ### Server:
34
+ ```bash
35
+ llama-server --hf-repo HDiffusion/Llama3-8b-CunnyGPT-16bit-Q4_K_M-GGUF --hf-file llama3-8b-cunnygpt-16bit-q4_k_m.gguf -c 2048
36
+ ```
37
+
38
+ 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.
39
+
40
+ Step 1: Clone llama.cpp from GitHub.
41
+ ```
42
+ git clone https://github.com/ggerganov/llama.cpp
43
+ ```
44
+
45
+ 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).
46
+ ```
47
+ cd llama.cpp && LLAMA_CURL=1 make
48
+ ```
49
+
50
+ Step 3: Run inference through the main binary.
51
+ ```
52
+ ./main --hf-repo HDiffusion/Llama3-8b-CunnyGPT-16bit-Q4_K_M-GGUF --hf-file llama3-8b-cunnygpt-16bit-q4_k_m.gguf -p "The meaning to life and the universe is"
53
+ ```
54
+ or
55
+ ```
56
+ ./server --hf-repo HDiffusion/Llama3-8b-CunnyGPT-16bit-Q4_K_M-GGUF --hf-file llama3-8b-cunnygpt-16bit-q4_k_m.gguf -c 2048
57
+ ```