itlwas commited on
Commit
3b2cbd0
·
verified ·
1 Parent(s): 198a50f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - HuggingFaceTB/cosmopedia
5
+ language:
6
+ - en
7
+ inference:
8
+ parameters:
9
+ temperature: 0.6
10
+ top_p: 0.95
11
+ top_k: 50
12
+ repetition_penalty: 1.2
13
+ widget:
14
+ - text: Photosynthesis is
15
+ example_title: Textbook
16
+ group: Completion
17
+ - text: '<s> [INST] How to take care of plants? [/INST] '
18
+ example_title: Wikihow
19
+ group: Completion
20
+ - text: '<s> [INST] Generate a story about a flying cat [/INST] '
21
+ example_title: Story
22
+ group: Completion
23
+ base_model: HuggingFaceTB/cosmo-1b
24
+ tags:
25
+ - llama-cpp
26
+ - gguf-my-repo
27
+ ---
28
+
29
+ # AIronMind/cosmo-1b-Q4_K_M-GGUF
30
+ This model was converted to GGUF format from [`HuggingFaceTB/cosmo-1b`](https://huggingface.co/HuggingFaceTB/cosmo-1b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
31
+ Refer to the [original model card](https://huggingface.co/HuggingFaceTB/cosmo-1b) for more details on the model.
32
+
33
+ ## Use with llama.cpp
34
+ Install llama.cpp through brew (works on Mac and Linux)
35
+
36
+ ```bash
37
+ brew install llama.cpp
38
+
39
+ ```
40
+ Invoke the llama.cpp server or the CLI.
41
+
42
+ ### CLI:
43
+ ```bash
44
+ llama-cli --hf-repo AIronMind/cosmo-1b-Q4_K_M-GGUF --hf-file cosmo-1b-q4_k_m.gguf -p "The meaning to life and the universe is"
45
+ ```
46
+
47
+ ### Server:
48
+ ```bash
49
+ llama-server --hf-repo AIronMind/cosmo-1b-Q4_K_M-GGUF --hf-file cosmo-1b-q4_k_m.gguf -c 2048
50
+ ```
51
+
52
+ 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.
53
+
54
+ Step 1: Clone llama.cpp from GitHub.
55
+ ```
56
+ git clone https://github.com/ggerganov/llama.cpp
57
+ ```
58
+
59
+ 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).
60
+ ```
61
+ cd llama.cpp && LLAMA_CURL=1 make
62
+ ```
63
+
64
+ Step 3: Run inference through the main binary.
65
+ ```
66
+ ./llama-cli --hf-repo AIronMind/cosmo-1b-Q4_K_M-GGUF --hf-file cosmo-1b-q4_k_m.gguf -p "The meaning to life and the universe is"
67
+ ```
68
+ or
69
+ ```
70
+ ./llama-server --hf-repo AIronMind/cosmo-1b-Q4_K_M-GGUF --hf-file cosmo-1b-q4_k_m.gguf -c 2048
71
+ ```