dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-25 13:04:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

chore(model gallery): add qwen3-14b-griffon-i1

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-07 11:05:23 +02:00
parent a86e8c78f1
commit 2a2421de53
1 changed files with 32 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

32
gallery/index.yaml
View file

@ -577,6 +577,38 @@
- filename: Claria-14b.Q4_K_M.gguf - filename: Claria-14b.Q4_K_M.gguf
sha256: 3173313c40ae487b3de8b07d757000bdbf86747333eba19880273be1fb38efab sha256: 3173313c40ae487b3de8b07d757000bdbf86747333eba19880273be1fb38efab
uri: huggingface://mradermacher/Claria-14b-GGUF/Claria-14b.Q4_K_M.gguf uri: huggingface://mradermacher/Claria-14b-GGUF/Claria-14b.Q4_K_M.gguf
- !!merge <<: *qwen3
name: "qwen3-14b-griffon-i1"
icon: https://huggingface.co/Daemontatox/Qwen3-14B-Griffon/resolve/main/image.png
urls:
- https://huggingface.co/Daemontatox/Qwen3-14B-Griffon
- https://huggingface.co/mradermacher/Qwen3-14B-Griffon-i1-GGUF
description: |
This is a fine-tuned version of the Qwen3-14B model using the high-quality OpenThoughts2-1M dataset. Fine-tuned with Unsloth’s TRL-compatible framework and LoRA for efficient performance, this model is optimized for advanced reasoning tasks, especially in math, logic puzzles, code generation, and step-by-step problem solving.
Training Dataset
Dataset: OpenThoughts2-1M
Source: A synthetic dataset curated and expanded by the OpenThoughts team
Volume: ~1.1M high-quality examples
Content Type: Multi-turn reasoning, math proofs, algorithmic code generation, logical deduction, and structured conversations
Tools Used: Curator Viewer
This dataset builds upon OpenThoughts-114k and integrates strong reasoning-centric data sources like OpenR1-Math and KodCode.
Intended Use
This model is particularly suited for:
Chain-of-thought and step-by-step reasoning
Code generation with logical structure
Educational tools for math and programming
AI agents requiring multi-turn problem-solving
overrides:
parameters:
model: Qwen3-14B-Griffon.i1-Q4_K_M.gguf
files:
- filename: Qwen3-14B-Griffon.i1-Q4_K_M.gguf
sha256: be4aed9a5061e7d43ea3e88f90a625bcfb6597c4224298e88d23b35285709cb4
uri: huggingface://mradermacher/Qwen3-14B-Griffon-i1-GGUF/Qwen3-14B-Griffon.i1-Q4_K_M.gguf
- &gemma3 - &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master" url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it" name: "gemma-3-27b-it"