matrixportal commited on
Commit
37dac59
1 Parent(s): d896c75

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: microsoft/Phi-3-medium-4k-instruct
3
+ language:
4
+ - multilingual
5
+ license: mit
6
+ license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - nlp
10
+ - code
11
+ - llama-cpp
12
+ - gguf-my-repo
13
+ inference:
14
+ parameters:
15
+ temperature: 0.7
16
+ widget:
17
+ - messages:
18
+ - role: user
19
+ content: Can you provide ways to eat combinations of bananas and dragonfruits?
20
+ ---
21
+
22
+ # matrixportal/Phi-3-medium-4k-instruct-Q4_K_M-GGUF
23
+ This model was converted to GGUF format from [`microsoft/Phi-3-medium-4k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-4k-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/microsoft/Phi-3-medium-4k-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 matrixportal/Phi-3-medium-4k-instruct-Q4_K_M-GGUF --hf-file phi-3-medium-4k-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
38
+ ```
39
+
40
+ ### Server:
41
+ ```bash
42
+ llama-server --hf-repo matrixportal/Phi-3-medium-4k-instruct-Q4_K_M-GGUF --hf-file phi-3-medium-4k-instruct-q4_k_m.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 matrixportal/Phi-3-medium-4k-instruct-Q4_K_M-GGUF --hf-file phi-3-medium-4k-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
60
+ ```
61
+ or
62
+ ```
63
+ ./llama-server --hf-repo matrixportal/Phi-3-medium-4k-instruct-Q4_K_M-GGUF --hf-file phi-3-medium-4k-instruct-q4_k_m.gguf -c 2048
64
+ ```