gallery: apply PR #11927

Assisted-by: localai-org-maint-bot:glm5.2 [gh]
This commit is contained in:
Ettore Di Giacinto committed 2026-09-11 22:37:15 +00:00
1 parent ab191912e9
commit 08a87788b4
1 file changed
+46 -1
+46 -1
View File
@@ -1,5 +1,50 @@
---
- name: "deepseek-v4-flash-vision-exp"
- name: "minicpm5-2b"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/openbmb/MiniCPM5-2B-GGUF
description: |
MiniCPM Tech Report |
MiniCPM Wiki(Chinese) |
GitHub Repo |
UltraData |
Online Demo
English |
中文
## Highlights
We are releasing **MiniCPM5-2B**, the second model in the **MiniCPM5** series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.
🏆 **2B-class open-source SOTA**: compared with strong open-source models of similar size, MiniCPM5-2B achieves SOTA performance within this comparison set. It remains competitive with 4B-class models overall, while showing its advantages over models of comparable size in coding, mathematics, long-context understanding, tool use, and agentic tasks.
...
license: "apache-2.0"
tags:
- llm
- gguf
- llama
icon: https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/minicpm5_2b_training_recipe.jpg
overrides:
backend: llama-cpp
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
options:
- use_jinja:true
parameters:
model: llama-cpp/models/MiniCPM5-2B-Q4_K_M/MiniCPM5-2B-Q4_K_M.gguf
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/MiniCPM5-2B-Q4_K_M/MiniCPM5-2B-Q4_K_M.gguf
sha256: ec2d5801640099e97d8d7e8003ad4d81f336e757811f03a26173dddf386602fd
uri: https://huggingface.co/openbmb/MiniCPM5-2B-GGUF/resolve/main/MiniCPM5-2B-Q4_K_M.gguf
- name: "qwopus3.8-27b-flash"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF