feat: add CAJAL gallery model (#9879)

Add the CAJAL GGUF gallery template and gallery index entry for local llama-cpp installs.

Assisted-by: Codex:gpt-5

Signed-off-by: Ching Kao <0980124jim@gmail.com>
Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com>
This commit is contained in:
Ching
2026-07-30 15:57:31 +08:00
committed by GitHub
parent 7a7ebb5c2f
commit 43b6ed2018
2 changed files with 44 additions and 0 deletions

16
gallery/cajal.yaml Normal file
View File

@@ -0,0 +1,16 @@
---
name: "cajal"
config_file: |
backend: llama-cpp
context_size: 32768
known_usecases:
- chat
- completion
function:
grammar:
disable: true
options:
- use_jinja:true
template:
use_tokenizer_template: true

View File

@@ -4656,6 +4656,34 @@
- filename: llama-cpp/mmproj/mmproj-Qwen_Qwen3.5-4B-f16.gguf
sha256: 659b59dd44b73b1cd34af6cc424669484b06dc80f4340adf8ea84ad776eef813
uri: https://huggingface.co/bartowski/Qwen_Qwen3.5-4B-GGUF/resolve/main/mmproj-Qwen_Qwen3.5-4B-f16.gguf
- name: cajal-4b-p2pclaw
url: github:mudler/LocalAI/gallery/cajal.yaml@master
urls:
- https://huggingface.co/Agnuxo/CAJAL-4B
- https://huggingface.co/Agnuxo/CAJAL-4B-P2PCLAW
- https://github.com/Agnuxo1/CAJAL
description: |
CAJAL-4B is a Qwen3.5-based 4B GGUF model specialized for scientific paper generation. It is tuned for academic structure, citation formats, LaTeX, and domain-specific technical writing within the P2PCLAW ecosystem, while remaining suitable for local llama-cpp inference.
license: apache-2.0
icon: https://huggingface.co/Agnuxo/CAJAL-4B-P2PCLAW/resolve/main/logo_cajal_blue.png
tags:
- cajal
- qwen3.5
- 4b
- gguf
- cpu
- gpu
- scientific-research
- academic-writing
- llama-cpp
last_checked: "2026-05-18"
overrides:
parameters:
model: llama-cpp/models/CAJAL-4B-q4_k_m.gguf
files:
- filename: llama-cpp/models/CAJAL-4B-q4_k_m.gguf
sha256: 4bce5383dc1dc4777b3812a2d944661e72d4572924af41df8d671e5da4772274
uri: https://huggingface.co/Agnuxo/CAJAL-4B/resolve/main/CAJAL-4B-q4_k_m.gguf
- name: qwen3.5-27b-claude-4.6-opus-reasoning-distilled-i1
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: