Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- FreedomIntelligence/ApolloMoEDataset
|
| 5 |
+
language:
|
| 6 |
+
- ar
|
| 7 |
+
- en
|
| 8 |
+
- zh
|
| 9 |
+
- ko
|
| 10 |
+
- ja
|
| 11 |
+
- mn
|
| 12 |
+
- th
|
| 13 |
+
- vi
|
| 14 |
+
- lo
|
| 15 |
+
- mg
|
| 16 |
+
- de
|
| 17 |
+
- pt
|
| 18 |
+
- es
|
| 19 |
+
- fr
|
| 20 |
+
- ru
|
| 21 |
+
- it
|
| 22 |
+
- hr
|
| 23 |
+
- gl
|
| 24 |
+
- cs
|
| 25 |
+
- co
|
| 26 |
+
- la
|
| 27 |
+
- uk
|
| 28 |
+
- bs
|
| 29 |
+
- bg
|
| 30 |
+
- eo
|
| 31 |
+
- sq
|
| 32 |
+
- da
|
| 33 |
+
- sa
|
| 34 |
+
- gn
|
| 35 |
+
- sr
|
| 36 |
+
- sk
|
| 37 |
+
- gd
|
| 38 |
+
- lb
|
| 39 |
+
- hi
|
| 40 |
+
- ku
|
| 41 |
+
- mt
|
| 42 |
+
- he
|
| 43 |
+
- ln
|
| 44 |
+
- bm
|
| 45 |
+
- sw
|
| 46 |
+
- ig
|
| 47 |
+
- rw
|
| 48 |
+
- ha
|
| 49 |
+
metrics:
|
| 50 |
+
- accuracy
|
| 51 |
+
base_model: FreedomIntelligence/Apollo2-2B
|
| 52 |
+
pipeline_tag: question-answering
|
| 53 |
+
tags:
|
| 54 |
+
- biology
|
| 55 |
+
- medical
|
| 56 |
+
- llama-cpp
|
| 57 |
+
- gguf-my-repo
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
# fernandoruiz/Apollo2-2B-Q4_0-GGUF
|
| 61 |
+
This model was converted to GGUF format from [`FreedomIntelligence/Apollo2-2B`](https://huggingface.co/FreedomIntelligence/Apollo2-2B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 62 |
+
Refer to the [original model card](https://huggingface.co/FreedomIntelligence/Apollo2-2B) for more details on the model.
|
| 63 |
+
|
| 64 |
+
## Use with llama.cpp
|
| 65 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
| 66 |
+
|
| 67 |
+
```bash
|
| 68 |
+
brew install llama.cpp
|
| 69 |
+
|
| 70 |
+
```
|
| 71 |
+
Invoke the llama.cpp server or the CLI.
|
| 72 |
+
|
| 73 |
+
### CLI:
|
| 74 |
+
```bash
|
| 75 |
+
llama-cli --hf-repo fernandoruiz/Apollo2-2B-Q4_0-GGUF --hf-file apollo2-2b-q4_0.gguf -p "The meaning to life and the universe is"
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
### Server:
|
| 79 |
+
```bash
|
| 80 |
+
llama-server --hf-repo fernandoruiz/Apollo2-2B-Q4_0-GGUF --hf-file apollo2-2b-q4_0.gguf -c 2048
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
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.
|
| 84 |
+
|
| 85 |
+
Step 1: Clone llama.cpp from GitHub.
|
| 86 |
+
```
|
| 87 |
+
git clone https://github.com/ggerganov/llama.cpp
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
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).
|
| 91 |
+
```
|
| 92 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
| 93 |
+
```
|
| 94 |
+
|
| 95 |
+
Step 3: Run inference through the main binary.
|
| 96 |
+
```
|
| 97 |
+
./llama-cli --hf-repo fernandoruiz/Apollo2-2B-Q4_0-GGUF --hf-file apollo2-2b-q4_0.gguf -p "The meaning to life and the universe is"
|
| 98 |
+
```
|
| 99 |
+
or
|
| 100 |
+
```
|
| 101 |
+
./llama-server --hf-repo fernandoruiz/Apollo2-2B-Q4_0-GGUF --hf-file apollo2-2b-q4_0.gguf -c 2048
|
| 102 |
+
```
|