Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,25 @@
|
|
1 |
-
---
|
2 |
-
license:
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
---
|
4 |
+
|
5 |
+
Quantized Llama 3 8B Instruct to Q40 format supported by [Distributed Llama](https://github.com/b4rtaz/distributed-llama).
|
6 |
+
|
7 |
+
## License
|
8 |
+
|
9 |
+
Before download this repository please accept [Llama 3 Community License](https://llama.meta.com/llama3/license/).
|
10 |
+
|
11 |
+
## How to run
|
12 |
+
|
13 |
+
1. Clone this repository.
|
14 |
+
2. Clone Distributed Llama:
|
15 |
+
```sh
|
16 |
+
git clone https://github.com/b4rtaz/distributed-llama.git
|
17 |
+
```
|
18 |
+
3. Build Distributed Llama:
|
19 |
+
```sh
|
20 |
+
make main
|
21 |
+
```
|
22 |
+
4. Run Distributed Llama:
|
23 |
+
```
|
24 |
+
./main inference --prompt "Hello world" --steps 128 --weights-float-type q40 --buffer-float-type q80 --nthreads 4 --model path/to/dllama_meta-llama-3-8b_q40.bin --tokenizer path/to/dllama_meta-llama3-tokenizer.t
|
25 |
+
```
|