Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: wtfpl
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- code
|
6 |
+
- llama-cpp
|
7 |
+
- gguf-my-repo
|
8 |
+
metrics:
|
9 |
+
- code_eval
|
10 |
+
model-index:
|
11 |
+
- name: WizardCoder
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
type: text-generation
|
15 |
+
dataset:
|
16 |
+
name: HumanEval
|
17 |
+
type: openai_humaneval
|
18 |
+
metrics:
|
19 |
+
- type: pass@1
|
20 |
+
value: 0.799
|
21 |
+
name: pass@1
|
22 |
+
verified: false
|
23 |
+
---
|
24 |
+
|
25 |
+
# win10/wizardcoder-33b-v1.1-mirror-Q2_K-GGUF
|
26 |
+
This model was converted to GGUF format from [`ChuckMcSneed/wizardcoder-33b-v1.1-mirror`](https://huggingface.co/ChuckMcSneed/wizardcoder-33b-v1.1-mirror) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
27 |
+
Refer to the [original model card](https://huggingface.co/ChuckMcSneed/wizardcoder-33b-v1.1-mirror) for more details on the model.
|
28 |
+
## Use with llama.cpp
|
29 |
+
Install llama.cpp through brew.
|
30 |
+
```bash
|
31 |
+
brew install ggerganov/ggerganov/llama.cpp
|
32 |
+
```
|
33 |
+
Invoke the llama.cpp server or the CLI.
|
34 |
+
CLI:
|
35 |
+
```bash
|
36 |
+
llama-cli --hf-repo win10/wizardcoder-33b-v1.1-mirror-Q2_K-GGUF --model wizardcoder-33b-v1.1-mirror-q2_k.gguf -p "The meaning to life and the universe is"
|
37 |
+
```
|
38 |
+
Server:
|
39 |
+
```bash
|
40 |
+
llama-server --hf-repo win10/wizardcoder-33b-v1.1-mirror-Q2_K-GGUF --model wizardcoder-33b-v1.1-mirror-q2_k.gguf -c 2048
|
41 |
+
```
|
42 |
+
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.
|
43 |
+
```
|
44 |
+
git clone https://github.com/ggerganov/llama.cpp && \
|
45 |
+
cd llama.cpp && \
|
46 |
+
make && \
|
47 |
+
./main -m wizardcoder-33b-v1.1-mirror-q2_k.gguf -n 128
|
48 |
+
```
|