dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

chore(model gallery): add agentica-org_deepcoder-14b-preview (#5151)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-09 16:55:47 +02:00 • committed by GitHub
parent 9c018e6bff
commit a69e30e0c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
gallery/index.yaml
View file

@ -8494,6 +8494,20 @@
- filename: Fallen-Safeword-70B-R1-v4.1.Q4_K_M.gguf
sha256: aed6bd5bb03b7bd886939237bc10ea6331d4feb5a3b6712e0c5474a778acf817
uri: huggingface://mradermacher/Fallen-Safeword-70B-R1-v4.1-GGUF/Fallen-Safeword-70B-R1-v4.1.Q4_K_M.gguf
- !!merge <<: *deepseek-r1
name: "agentica-org_deepcoder-14b-preview"
urls:
- https://huggingface.co/agentica-org/DeepCoder-14B-Preview
- https://huggingface.co/bartowski/agentica-org_DeepCoder-14B-Preview-GGUF
description: |
DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters.
overrides:
parameters:
model: agentica-org_DeepCoder-14B-Preview-Q4_K_M.gguf
files:
- filename: agentica-org_DeepCoder-14B-Preview-Q4_K_M.gguf
sha256: 38f0f777de3116ca27d10ec84388b3290a1bf3f7db8c5bdc1f92d100e4231870
uri: huggingface://bartowski/agentica-org_DeepCoder-14B-Preview-GGUF/agentica-org_DeepCoder-14B-Preview-Q4_K_M.gguf
- &qwen2
url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2
name: "qwen2-7b-instruct"