Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- multilingual
|
| 4 |
+
- ar
|
| 5 |
+
- zh
|
| 6 |
+
- cs
|
| 7 |
+
- da
|
| 8 |
+
- nl
|
| 9 |
+
- en
|
| 10 |
+
- fi
|
| 11 |
+
- fr
|
| 12 |
+
- de
|
| 13 |
+
- he
|
| 14 |
+
- hu
|
| 15 |
+
- it
|
| 16 |
+
- ja
|
| 17 |
+
- ko
|
| 18 |
+
- 'no'
|
| 19 |
+
- pl
|
| 20 |
+
- pt
|
| 21 |
+
- ru
|
| 22 |
+
- es
|
| 23 |
+
- sv
|
| 24 |
+
- th
|
| 25 |
+
- tr
|
| 26 |
+
- uk
|
| 27 |
+
library_name: transformers
|
| 28 |
+
license: mit
|
| 29 |
+
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE
|
| 30 |
+
pipeline_tag: text-generation
|
| 31 |
+
tags:
|
| 32 |
+
- nlp
|
| 33 |
+
- code
|
| 34 |
+
- llama-cpp
|
| 35 |
+
- gguf-my-repo
|
| 36 |
+
widget:
|
| 37 |
+
- messages:
|
| 38 |
+
- role: user
|
| 39 |
+
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
| 40 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
# akshaykdeo/Phi-4-mini-instruct-Q4_K_M-GGUF
|
| 44 |
+
This model was converted to GGUF format from [`microsoft/Phi-4-mini-instruct`](https://huggingface.co/microsoft/Phi-4-mini-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 45 |
+
Refer to the [original model card](https://huggingface.co/microsoft/Phi-4-mini-instruct) for more details on the model.
|
| 46 |
+
|
| 47 |
+
## Use with llama.cpp
|
| 48 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
| 49 |
+
|
| 50 |
+
```bash
|
| 51 |
+
brew install llama.cpp
|
| 52 |
+
|
| 53 |
+
```
|
| 54 |
+
Invoke the llama.cpp server or the CLI.
|
| 55 |
+
|
| 56 |
+
### CLI:
|
| 57 |
+
```bash
|
| 58 |
+
llama-cli --hf-repo akshaykdeo/Phi-4-mini-instruct-Q4_K_M-GGUF --hf-file phi-4-mini-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
### Server:
|
| 62 |
+
```bash
|
| 63 |
+
llama-server --hf-repo akshaykdeo/Phi-4-mini-instruct-Q4_K_M-GGUF --hf-file phi-4-mini-instruct-q4_k_m.gguf -c 2048
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
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.
|
| 67 |
+
|
| 68 |
+
Step 1: Clone llama.cpp from GitHub.
|
| 69 |
+
```
|
| 70 |
+
git clone https://github.com/ggerganov/llama.cpp
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
+
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).
|
| 74 |
+
```
|
| 75 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
Step 3: Run inference through the main binary.
|
| 79 |
+
```
|
| 80 |
+
./llama-cli --hf-repo akshaykdeo/Phi-4-mini-instruct-Q4_K_M-GGUF --hf-file phi-4-mini-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
|
| 81 |
+
```
|
| 82 |
+
or
|
| 83 |
+
```
|
| 84 |
+
./llama-server --hf-repo akshaykdeo/Phi-4-mini-instruct-Q4_K_M-GGUF --hf-file phi-4-mini-instruct-q4_k_m.gguf -c 2048
|
| 85 |
+
```
|