DavidAU commited on
Commit
4953c6e
1 Parent(s): 5fab076

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+ - Mistral
10
+ - instruct
11
+ - finetune
12
+ - chatml
13
+ - DPO
14
+ - RLHF
15
+ - gpt4
16
+ - synthetic data
17
+ - distillation
18
+ - function calling
19
+ - json mode
20
+ - llama-cpp
21
+ - gguf-my-repo
22
+ base_model: mistralai/Mistral-7B-v0.1
23
+ datasets:
24
+ - teknium/OpenHermes-2.5
25
+ widget:
26
+ - example_title: Hermes 2 Pro
27
+ messages:
28
+ - role: system
29
+ content: You are a sentient, superintelligent artificial general intelligence,
30
+ here to teach and assist me.
31
+ - role: user
32
+ content: Write a short story about Goku discovering kirby has teamed up with Majin
33
+ Buu to destroy the world.
34
+ model-index:
35
+ - name: Hermes-2-Pro-Mistral-10.7B
36
+ results: []
37
+ ---
38
+
39
+ # DavidAU/Hermes-2-Pro-Mistral-10.7B-Q6_K-GGUF
40
+ This model was converted to GGUF format from [`Joseph717171/Hermes-2-Pro-Mistral-10.7B`](https://huggingface.co/Joseph717171/Hermes-2-Pro-Mistral-10.7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
41
+ Refer to the [original model card](https://huggingface.co/Joseph717171/Hermes-2-Pro-Mistral-10.7B) for more details on the model.
42
+ ## Use with llama.cpp
43
+
44
+ Install llama.cpp through brew.
45
+
46
+ ```bash
47
+ brew install ggerganov/ggerganov/llama.cpp
48
+ ```
49
+ Invoke the llama.cpp server or the CLI.
50
+
51
+ CLI:
52
+
53
+ ```bash
54
+ llama-cli --hf-repo DavidAU/Hermes-2-Pro-Mistral-10.7B-Q6_K-GGUF --model hermes-2-pro-mistral-10.7b.Q6_K.gguf -p "The meaning to life and the universe is"
55
+ ```
56
+
57
+ Server:
58
+
59
+ ```bash
60
+ llama-server --hf-repo DavidAU/Hermes-2-Pro-Mistral-10.7B-Q6_K-GGUF --model hermes-2-pro-mistral-10.7b.Q6_K.gguf -c 2048
61
+ ```
62
+
63
+ 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.
64
+
65
+ ```
66
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m hermes-2-pro-mistral-10.7b.Q6_K.gguf -n 128
67
+ ```