Sri-Vigneshwar-DJ commited on
Commit
d35e9d6
·
verified ·
1 Parent(s): cb3638f

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - vicuna-7b-v1.5
4
+ - lmsys/vicuna-7b-v1.5
5
+ library_name: transformers
6
+ license: other
7
+ tags:
8
+ - llama-cpp
9
+ - vicuna
10
+ - vicuna-7b-v1.5
11
+ - vicuna-7b
12
+ - GGUF
13
+ ---
14
+
15
+ # Sri-Vigneshwar-DJ/hawky-ai-vicuna-7b-v1.5-GGUF
16
+ This model was converted to GGUF format from [`google/gemma-2-9b`](https://huggingface.co/google/gemma-2-9b) using llama.cpp
17
+ Refer to the [original model card](https://huggingface.co/google/gemma-2-9b) for more details on the model.
18
+
19
+ ## Use with llama.cpp
20
+ Install llama.cpp through brew (works on Mac and Linux) from []
21
+
22
+ ```bash
23
+ brew install llama.cpp or !git clone https://github.com/ggerganov/llama.cpp.git
24
+
25
+ ```
26
+ Invoke the llama.cpp server or the CLI.
27
+
28
+ ### CLI:
29
+ ```bash
30
+ ! /content/llama.cpp/llama-cli -m ./marketing/FP16.gguf -n 90 --repeat_penalty 1.0 --color -i -r "User:" -f /content/llama.cpp/prompts/chat-with-bob.txt
31
+
32
+ or
33
+
34
+ llama-cli --hf-repo Sri-Vigneshwar-DJ/hawky-ai-vicuna-7b-v1.5-GGUF --hf-file FP8.gguf -p "Write content for 'Facebook Post - About AI'"
35
+ ```
36
+
37
+ ### Server:
38
+ ```bash
39
+ llama-server --hf-repo Sri-Vigneshwar-DJ/hawky-ai-vicuna-7b-v1.5-GGUF --hf-file FP8.gguf -c 2048
40
+ ```
41
+
42
+ 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.
43
+
44
+ Step 1: Clone llama.cpp from GitHub.
45
+ ```
46
+ git clone https://github.com/ggerganov/llama.cpp
47
+ ```
48
+
49
+ Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag or ''!make GGML_OPENBLAS=1' along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
50
+ ```
51
+ cd llama.cpp && LLAMA_CURL=1 make
52
+
53
+ or
54
+
55
+ !make GGML_OPENBLAS=1
56
+ ```
57
+
58
+ Step 3: Run inference through the main binary.
59
+ ```
60
+ ./llama-cli --hf-repo Sri-Vigneshwar-DJ/hawky-ai-vicuna-7b-v1.5-GGUF --hf-file FP8.gguf -p "The meaning to life and the universe is"
61
+ ```
62
+ or
63
+ ```
64
+ ./llama-server --hf-repo Sri-Vigneshwar-DJ/hawky-ai-vicuna-7b-v1.5-GGUF --hf-file sFP8.gguf -c 2048
65
+ ```