Julia-Kovacs commited on
Commit
58f9eb7
1 Parent(s): 7453b58

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - hu
4
+ - en
5
+ license: llama2
6
+ tags:
7
+ - llama-cpp
8
+ - gguf-my-repo
9
+ base_model: sambanovasystems/SambaLingo-Hungarian-Base-70B
10
+ datasets:
11
+ - uonlp/CulturaX
12
+ metrics:
13
+ - chrf
14
+ - accuracy
15
+ - bleu
16
+ ---
17
+
18
+ # Julia-Kovacs/SambaLingo-Hungarian-Base-70B-Q4_K_M-GGUF
19
+ This model was converted to GGUF format from [`sambanovasystems/SambaLingo-Hungarian-Base-70B`](https://huggingface.co/sambanovasystems/SambaLingo-Hungarian-Base-70B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
20
+ Refer to the [original model card](https://huggingface.co/sambanovasystems/SambaLingo-Hungarian-Base-70B) for more details on the model.
21
+
22
+ ## Use with llama.cpp
23
+ Install llama.cpp through brew (works on Mac and Linux)
24
+
25
+ ```bash
26
+ brew install llama.cpp
27
+
28
+ ```
29
+ Invoke the llama.cpp server or the CLI.
30
+
31
+ ### CLI:
32
+ ```bash
33
+ llama --hf-repo Julia-Kovacs/SambaLingo-Hungarian-Base-70B-Q4_K_M-GGUF --hf-file sambalingo-hungarian-base-70b-q4_k_m.gguf -p "The meaning to life and the universe is"
34
+ ```
35
+
36
+ ### Server:
37
+ ```bash
38
+ llama-server --hf-repo Julia-Kovacs/SambaLingo-Hungarian-Base-70B-Q4_K_M-GGUF --hf-file sambalingo-hungarian-base-70b-q4_k_m.gguf -c 2048
39
+ ```
40
+
41
+ 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 1: Clone llama.cpp from GitHub.
44
+ ```
45
+ git clone https://github.com/ggerganov/llama.cpp
46
+ ```
47
+
48
+ 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).
49
+ ```
50
+ cd llama.cpp && LLAMA_CURL=1 make
51
+ ```
52
+
53
+ Step 3: Run inference through the main binary.
54
+ ```
55
+ ./main --hf-repo Julia-Kovacs/SambaLingo-Hungarian-Base-70B-Q4_K_M-GGUF --hf-file sambalingo-hungarian-base-70b-q4_k_m.gguf -p "The meaning to life and the universe is"
56
+ ```
57
+ or
58
+ ```
59
+ ./server --hf-repo Julia-Kovacs/SambaLingo-Hungarian-Base-70B-Q4_K_M-GGUF --hf-file sambalingo-hungarian-base-70b-q4_k_m.gguf -c 2048
60
+ ```