Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- chat
|
7 |
+
- llama-cpp
|
8 |
+
- gguf-my-repo
|
9 |
+
base_model: Qwen/Qwen2-7B-Instruct
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
---
|
12 |
+
|
13 |
+
# shajmaan/Qwen2-7B-Instruct-Q4_0-GGUF
|
14 |
+
This model was converted to GGUF format from [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
15 |
+
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2-7B-Instruct) for more details on the model.
|
16 |
+
|
17 |
+
## Use with llama.cpp
|
18 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
19 |
+
|
20 |
+
```bash
|
21 |
+
brew install llama.cpp
|
22 |
+
|
23 |
+
```
|
24 |
+
Invoke the llama.cpp server or the CLI.
|
25 |
+
|
26 |
+
### CLI:
|
27 |
+
```bash
|
28 |
+
llama --hf-repo shajmaan/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -p "The meaning to life and the universe is"
|
29 |
+
```
|
30 |
+
|
31 |
+
### Server:
|
32 |
+
```bash
|
33 |
+
llama-server --hf-repo shajmaan/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -c 2048
|
34 |
+
```
|
35 |
+
|
36 |
+
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.
|
37 |
+
|
38 |
+
Step 1: Clone llama.cpp from GitHub.
|
39 |
+
```
|
40 |
+
git clone https://github.com/ggerganov/llama.cpp
|
41 |
+
```
|
42 |
+
|
43 |
+
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).
|
44 |
+
```
|
45 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
46 |
+
```
|
47 |
+
|
48 |
+
Step 3: Run inference through the main binary.
|
49 |
+
```
|
50 |
+
./main --hf-repo shajmaan/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -p "The meaning to life and the universe is"
|
51 |
+
```
|
52 |
+
or
|
53 |
+
```
|
54 |
+
./server --hf-repo shajmaan/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -c 2048
|
55 |
+
```
|