Skip to content

Commit 764c976

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 c03e532 commit 764c976

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: "thinkfl-llama3-8b"
3+
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
4+
urls:
5+
- https://huggingface.co/mradermacher/ThinkFL-Llama3-8B-GGUF
6+
description: |
7+
The model is a quantized version of the official Llama3-8B model, optimized for efficiency with GGUF format. It retains the core capabilities of the original model while being reduced in precision (e.g., Q4_K_S, Q2_K, Q8_0) to lower computational demands. The quantization reduces memory usage and inference speed without sacrificing performance, making it suitable for deployment in resource-constrained environments.
8+
overrides:
9+
parameters:
10+
model: llama-cpp/models/ThinkFL-Llama3-8B.Q4_K_M.gguf
11+
name: ThinkFL-Llama3-8B-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/mradermacher/ThinkFL-Llama3-8B-GGUF
21+
options:
22+
- use_jinja:true
23+
files:
24+
- filename: llama-cpp/models/ThinkFL-Llama3-8B.Q4_K_M.gguf
25+
sha256: f83a572952eb838c0d38791e53a8b16ac8bb3786560e2f99299f396f130de8eb
26+
uri: https://huggingface.co/mradermacher/ThinkFL-Llama3-8B-GGUF/resolve/main/ThinkFL-Llama3-8B.Q4_K_M.gguf
227
- name: "lfm2.5-1.2b-nova-function-calling"
328
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
429
urls:

0 commit comments

Comments
 (0)