NikolayKozloff commited on
Commit
8fd32d6
1 Parent(s): 9ac14e2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: haqishen/h2o-Llama-3-8B-Japanese-Instruct
3
+ datasets:
4
+ - fujiki/japanese_hh-rlhf-49k
5
+ language:
6
+ - en
7
+ - ja
8
+ library_name: transformers
9
+ license: llama3
10
+ pipeline_tag: text-generation
11
+ tags:
12
+ - gpt
13
+ - llm
14
+ - large language model
15
+ - h2o-llmstudio
16
+ - llama-cpp
17
+ - gguf-my-repo
18
+ inference: false
19
+ thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
20
+ ---
21
+
22
+ # NikolayKozloff/h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF
23
+ This model was converted to GGUF format from [`haqishen/h2o-Llama-3-8B-Japanese-Instruct`](https://huggingface.co/haqishen/h2o-Llama-3-8B-Japanese-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
24
+ Refer to the [original model card](https://huggingface.co/haqishen/h2o-Llama-3-8B-Japanese-Instruct) for more details on the model.
25
+
26
+ ## Use with llama.cpp
27
+ Install llama.cpp through brew (works on Mac and Linux)
28
+
29
+ ```bash
30
+ brew install llama.cpp
31
+
32
+ ```
33
+ Invoke the llama.cpp server or the CLI.
34
+
35
+ ### CLI:
36
+ ```bash
37
+ llama-cli --hf-repo NikolayKozloff/h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF --hf-file h2o-llama-3-8b-japanese-instruct-q8_0.gguf -p "The meaning to life and the universe is"
38
+ ```
39
+
40
+ ### Server:
41
+ ```bash
42
+ llama-server --hf-repo NikolayKozloff/h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF --hf-file h2o-llama-3-8b-japanese-instruct-q8_0.gguf -c 2048
43
+ ```
44
+
45
+ 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.
46
+
47
+ Step 1: Clone llama.cpp from GitHub.
48
+ ```
49
+ git clone https://github.com/ggerganov/llama.cpp
50
+ ```
51
+
52
+ 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).
53
+ ```
54
+ cd llama.cpp && LLAMA_CURL=1 make
55
+ ```
56
+
57
+ Step 3: Run inference through the main binary.
58
+ ```
59
+ ./llama-cli --hf-repo NikolayKozloff/h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF --hf-file h2o-llama-3-8b-japanese-instruct-q8_0.gguf -p "The meaning to life and the universe is"
60
+ ```
61
+ or
62
+ ```
63
+ ./llama-server --hf-repo NikolayKozloff/h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF --hf-file h2o-llama-3-8b-japanese-instruct-q8_0.gguf -c 2048
64
+ ```