Instructions to use deymon3522/shimaore-ia-ios-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use deymon3522/shimaore-ia-ios-models with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- Qwen2.5-0.5B-Instruct_multi-prefill-seq_q8_ekv1280.task +3 -0
- README.md +30 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Qwen2.5-0.5B-Instruct_multi-prefill-seq_q8_ekv1280.task filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-0.5B-Instruct_multi-prefill-seq_q8_ekv1280.task
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e608953f169aeb1bd7b9155fec2559825e08453fc209b84eda3a781ed0452fd2
|
| 3 |
+
size 546660344
|
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- ios
|
| 5 |
+
- mediapipe
|
| 6 |
+
- litert
|
| 7 |
+
- qwen
|
| 8 |
+
- shimaore-app
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Shimaore App iOS Models
|
| 12 |
+
|
| 13 |
+
Depot public de modeles iOS telechargeables directement par l'application Shimaore.
|
| 14 |
+
|
| 15 |
+
## Objectif
|
| 16 |
+
|
| 17 |
+
Fournir des fichiers `.task` compatibles avec l'application iOS actuelle.
|
| 18 |
+
|
| 19 |
+
## Contenu actuel
|
| 20 |
+
|
| 21 |
+
- `Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv1280.task`
|
| 22 |
+
|
| 23 |
+
## Note
|
| 24 |
+
|
| 25 |
+
Le comportement shimaore specifique de l'application repose encore sur:
|
| 26 |
+
- le dictionnaire local embarque
|
| 27 |
+
- les corrections RAG cote application
|
| 28 |
+
|
| 29 |
+
Le fine-tune Gemma 4 experimental est publie a part, mais il n'est pas encore integre ici car il n'existe pas encore sous forme de bundle iOS public fiable pour cette application.
|
| 30 |
+
|