nvhf commited on
Commit
aa88843
1 Parent(s): 6f4c642

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: grammarly/coedit-xl
3
+ datasets:
4
+ - grammarly/coedit
5
+ - facebook/asset
6
+ - jfleg
7
+ - zaemyung/IteraTeR_plus
8
+ - wi_locness
9
+ - GEM/wiki_auto_asset_turk
10
+ - discofuse
11
+ language:
12
+ - en
13
+ license: cc-by-nc-4.0
14
+ metrics:
15
+ - sari
16
+ - bleu
17
+ - accuracy
18
+ tags:
19
+ - llama-cpp
20
+ - gguf-my-repo
21
+ ---
22
+
23
+ # nvhf/coedit-xl-Q6_K-GGUF
24
+ This model was converted to GGUF format from [`grammarly/coedit-xl`](https://huggingface.co/grammarly/coedit-xl) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
25
+ Refer to the [original model card](https://huggingface.co/grammarly/coedit-xl) for more details on the model.
26
+
27
+ ## Use with llama.cpp
28
+ Install llama.cpp through brew (works on Mac and Linux)
29
+
30
+ ```bash
31
+ brew install llama.cpp
32
+
33
+ ```
34
+ Invoke the llama.cpp server or the CLI.
35
+
36
+ ### CLI:
37
+ ```bash
38
+ llama-cli --hf-repo nvhf/coedit-xl-Q6_K-GGUF --hf-file coedit-xl-q6_k.gguf -p "The meaning to life and the universe is"
39
+ ```
40
+
41
+ ### Server:
42
+ ```bash
43
+ llama-server --hf-repo nvhf/coedit-xl-Q6_K-GGUF --hf-file coedit-xl-q6_k.gguf -c 2048
44
+ ```
45
+
46
+ 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.
47
+
48
+ Step 1: Clone llama.cpp from GitHub.
49
+ ```
50
+ git clone https://github.com/ggerganov/llama.cpp
51
+ ```
52
+
53
+ 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).
54
+ ```
55
+ cd llama.cpp && LLAMA_CURL=1 make
56
+ ```
57
+
58
+ Step 3: Run inference through the main binary.
59
+ ```
60
+ ./llama-cli --hf-repo nvhf/coedit-xl-Q6_K-GGUF --hf-file coedit-xl-q6_k.gguf -p "The meaning to life and the universe is"
61
+ ```
62
+ or
63
+ ```
64
+ ./llama-server --hf-repo nvhf/coedit-xl-Q6_K-GGUF --hf-file coedit-xl-q6_k.gguf -c 2048
65
+ ```