Skip to content

Commit 9978b91

Browse files
mudlergithub-actions[bot]
authored andcommitted
chore(model gallery): 🤖 add new models via gallery agent
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
1 parent 820bd7d commit 9978b91

File tree

1 file changed

+25
-0
lines changed

1 file changed

+25
-0
lines changed

gallery/index.yaml

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,29 @@
11
---
2+
- name: "magibu-11b"
3+
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
4+
urls:
5+
- https://huggingface.co/alibayram/magibu-11b-Q4_K_M-GGUF
6+
description: |
7+
The model `alibayram/magibu-11b-Q4_K_M-GGUF` is a quantized version of the base model `alibayram/magibu-11b`, converted to the GGUF format for efficient deployment. It supports inference via llama.cpp, with 4-bit quantization (Q4_K_M) for reduced memory usage. The model is optimized for performance and is suitable for tasks like text generation, reasoning, and multilingual support. For usage, install llama.cpp via Homebrew and run the CLI or server with the GGUF file. This version is a direct derivative of the original model, retaining its capabilities while optimizing for efficiency.
8+
overrides:
9+
parameters:
10+
model: llama-cpp/models/magibu-11b-q4_k_m.gguf
11+
name: magibu-11b-Q4_K_M-GGUF
12+
backend: llama-cpp
13+
template:
14+
use_tokenizer_template: true
15+
known_usecases:
16+
- chat
17+
function:
18+
grammar:
19+
disable: true
20+
description: Imported from https://huggingface.co/alibayram/magibu-11b-Q4_K_M-GGUF
21+
options:
22+
- use_jinja:true
23+
files:
24+
- filename: llama-cpp/models/magibu-11b-q4_k_m.gguf
25+
sha256: 4aab1c4737d51e97849d7b8d95445c314574ad998f57acc6cb718519534d8018
26+
uri: https://huggingface.co/alibayram/magibu-11b-Q4_K_M-GGUF/resolve/main/magibu-11b-q4_k_m.gguf
227
- &nanbeige4
328
name: "nanbeige4.1-3b-q8"
429
url: "github:mudler/LocalAI/gallery/nanbeige4.1.yaml@master"

0 commit comments

Comments
 (0)