mattritchey commited on
Commit
94cb88a
·
verified ·
1 Parent(s): 31fa0f4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +61 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: fblgit/pancho-v1-qw25-3B-UNAMGS
5
+ tags:
6
+ - generated_from_trainer
7
+ - llama-cpp
8
+ - gguf-my-repo
9
+ datasets:
10
+ - Magpie-Align/Magpie-Pro-MT-300K-v0.1
11
+ - Magpie-Align/Magpie-Llama-3.1-Pro-MT-300K-Filtered
12
+ language:
13
+ - en
14
+ model-index:
15
+ - name: pancho-v1-qw25-3B-UNAMGS
16
+ results: []
17
+ ---
18
+
19
+ # mattritchey/pancho-v1-qw25-3B-UNAMGS-Q4_K_M-GGUF
20
+ This model was converted to GGUF format from [`fblgit/pancho-v1-qw25-3B-UNAMGS`](https://huggingface.co/fblgit/pancho-v1-qw25-3B-UNAMGS) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
21
+ Refer to the [original model card](https://huggingface.co/fblgit/pancho-v1-qw25-3B-UNAMGS) for more details on the model.
22
+
23
+ ## Use with llama.cpp
24
+ Install llama.cpp through brew (works on Mac and Linux)
25
+
26
+ ```bash
27
+ brew install llama.cpp
28
+
29
+ ```
30
+ Invoke the llama.cpp server or the CLI.
31
+
32
+ ### CLI:
33
+ ```bash
34
+ llama-cli --hf-repo mattritchey/pancho-v1-qw25-3B-UNAMGS-Q4_K_M-GGUF --hf-file pancho-v1-qw25-3b-unamgs-q4_k_m.gguf -p "The meaning to life and the universe is"
35
+ ```
36
+
37
+ ### Server:
38
+ ```bash
39
+ llama-server --hf-repo mattritchey/pancho-v1-qw25-3B-UNAMGS-Q4_K_M-GGUF --hf-file pancho-v1-qw25-3b-unamgs-q4_k_m.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 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
+
54
+ Step 3: Run inference through the main binary.
55
+ ```
56
+ ./llama-cli --hf-repo mattritchey/pancho-v1-qw25-3B-UNAMGS-Q4_K_M-GGUF --hf-file pancho-v1-qw25-3b-unamgs-q4_k_m.gguf -p "The meaning to life and the universe is"
57
+ ```
58
+ or
59
+ ```
60
+ ./llama-server --hf-repo mattritchey/pancho-v1-qw25-3B-UNAMGS-Q4_K_M-GGUF --hf-file pancho-v1-qw25-3b-unamgs-q4_k_m.gguf -c 2048
61
+ ```