Rybens commited on
Commit
6688d52
1 Parent(s): 12148cd

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ language:
4
+ - en
5
+ license: llama3
6
+ tags:
7
+ - Llama-3
8
+ - instruct
9
+ - finetune
10
+ - chatml
11
+ - gpt4
12
+ - synthetic data
13
+ - distillation
14
+ - function calling
15
+ - json mode
16
+ - axolotl
17
+ - roleplaying
18
+ - chat
19
+ - llama-cpp
20
+ - gguf-my-repo
21
+ widget:
22
+ - example_title: Hermes 3
23
+ messages:
24
+ - role: system
25
+ content: You are a sentient, superintelligent artificial general intelligence,
26
+ here to teach and assist me.
27
+ - role: user
28
+ content: What is the meaning of life?
29
+ model-index:
30
+ - name: Hermes-3-Llama-3.1-70B
31
+ results: []
32
+ ---
33
+
34
+ # Rybens/Hermes-3-Llama-3.1-8B-Q3_K_S-GGUF
35
+ This model was converted to GGUF format from [`NousResearch/Hermes-3-Llama-3.1-8B`](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
36
+ Refer to the [original model card](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) for more details on the model.
37
+
38
+ ## Use with llama.cpp
39
+ Install llama.cpp through brew (works on Mac and Linux)
40
+
41
+ ```bash
42
+ brew install llama.cpp
43
+
44
+ ```
45
+ Invoke the llama.cpp server or the CLI.
46
+
47
+ ### CLI:
48
+ ```bash
49
+ llama-cli --hf-repo Rybens/Hermes-3-Llama-3.1-8B-Q3_K_S-GGUF --hf-file hermes-3-llama-3.1-8b-q3_k_s.gguf -p "The meaning to life and the universe is"
50
+ ```
51
+
52
+ ### Server:
53
+ ```bash
54
+ llama-server --hf-repo Rybens/Hermes-3-Llama-3.1-8B-Q3_K_S-GGUF --hf-file hermes-3-llama-3.1-8b-q3_k_s.gguf -c 2048
55
+ ```
56
+
57
+ 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.
58
+
59
+ Step 1: Clone llama.cpp from GitHub.
60
+ ```
61
+ git clone https://github.com/ggerganov/llama.cpp
62
+ ```
63
+
64
+ 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).
65
+ ```
66
+ cd llama.cpp && LLAMA_CURL=1 make
67
+ ```
68
+
69
+ Step 3: Run inference through the main binary.
70
+ ```
71
+ ./llama-cli --hf-repo Rybens/Hermes-3-Llama-3.1-8B-Q3_K_S-GGUF --hf-file hermes-3-llama-3.1-8b-q3_k_s.gguf -p "The meaning to life and the universe is"
72
+ ```
73
+ or
74
+ ```
75
+ ./llama-server --hf-repo Rybens/Hermes-3-Llama-3.1-8B-Q3_K_S-GGUF --hf-file hermes-3-llama-3.1-8b-q3_k_s.gguf -c 2048
76
+ ```