af0d68d611
nit: combine temperatureMetrics and useFahrenheit
2025-10-28 11:39:16 -07:00
5e4972e93e
UI: refactor top app bars
2025-10-28 11:39:16 -07:00
2a41c0e354
vm: replace token metrics stubs with actual implementation
2025-10-28 11:39:16 -07:00
e47e3b77ee
UI: locks user in alert dialog when model is unloading
2025-10-28 11:39:16 -07:00
6b341b0fbe
bugfix: handle user quitting on model loading
2025-10-28 11:39:16 -07:00
e8b84c6ebf
UI: code polish
2025-10-28 11:39:16 -07:00
fddf060d92
data: code polish
2025-10-28 11:39:16 -07:00
3b499ac7e4
UI: polish conversation screen
2025-10-28 11:39:16 -07:00
64ebdc67a6
UI: update app name to be more Arm
2025-10-28 11:39:16 -07:00
55681847e9
UI: rename `ModeSelection` to `ModelLoading` for better clarity
2025-10-28 11:39:16 -07:00
75c986afc5
bugfix: properly handle user's quitting conversation screen while tokens in generation
2025-10-28 11:39:16 -07:00
4848bf93d0
data: introduce repo for System Prompt; flow data from Room to VM
2025-10-28 11:39:16 -07:00
5596d5203b
DB: setup Room database
2025-10-28 11:39:16 -07:00
4046cd16fd
Deps: bump Kotlin plugin; introduce KSP; apply in :app subproject
2025-10-28 11:39:16 -07:00
5868eaa66b
UI: polish system prompt setup UI
2025-10-28 11:39:16 -07:00
a7ee3d305f
UI: split a nested parent settings screen into separate child settings screens
2025-10-28 11:39:16 -07:00
65c09b2b32
UI: allow drawer's gesture control only on Home and Settings screens; enable alert dialog on back navigation inside conversation and benchmark
2025-10-28 11:39:16 -07:00
648b97818e
UI: disable triggering drawer via gesture; enable alert dialog on back navigation inside conversation and benchmark
2025-10-28 11:39:16 -07:00
a7ae8b7ce0
[WIP] DI: implement simple local vm factory provider
2025-10-28 11:39:16 -07:00
ca2b7772ce
UI: add a new MainActivity; update manifest
2025-10-28 11:39:16 -07:00
7e5c80cee9
UI: implement core flow's screens
2025-10-28 11:39:16 -07:00
5ad65919e9
util: implement user preferences utility
2025-10-28 11:39:16 -07:00
46bd638c5f
util: implement performance monitor; wrap it with a viewmodel
2025-10-28 11:39:16 -07:00
4dd755e25b
UI: implement basic UI components
2025-10-28 11:39:16 -07:00
32608fb225
UI: app navigation
2025-10-28 11:39:16 -07:00
3f913ce440
LLM: stub a local inference engine for faster iteration
2025-10-28 11:39:16 -07:00
3787fbddb0
data: define data models for LLM and system prompts
2025-10-28 11:39:16 -07:00
697d778db7
UI: define theme, color palette, typography and shape
2025-10-28 11:39:16 -07:00
cbe7133742
UI: introduce new dependencies, update versions & references
2025-10-28 11:39:16 -07:00
44a522dbc8
UI: move existing UI src files into `legacy` package
2025-10-28 11:39:16 -07:00
37f3e1c415
Feature: use local llama_context for benchmarking; support context init with custom context size
2025-10-28 11:39:16 -07:00
6d2279e9cd
REWRITE JNI bridge; Update viewmodel
2025-10-28 11:39:16 -07:00
e1bc87610e
Perf: allocate `llama_batch` on stack with `llama_batch_init`
2025-10-28 11:39:16 -07:00
2b52563737
Polish: better logging & documentation
2025-10-28 11:39:16 -07:00
ec502cfde9
Feature: implement infinite conversation via context shifting
2025-10-28 11:39:16 -07:00
4e515727b4
Abort on system prompt too long; Truncate user prompt if too long.
2025-10-28 11:39:16 -07:00
4809112ec5
Polish: adopt common naming; init modularization;
2025-10-28 11:39:16 -07:00
8bf2f4d412
Feature: chat template auto formatting
2025-10-28 11:39:16 -07:00
1b0754c0f5
Perf: optimize performance with ARM features
2025-10-28 11:39:16 -07:00
bb5b824208
Polish: populate backend names in `benchModel`
2025-10-28 11:39:16 -07:00
c14c11dcbd
Feature: decode system and user prompt in batches
2025-10-28 11:39:16 -07:00
02465137ca
Bug fix: null system prompt state update; Safeguard empty user prompt
2025-10-28 11:39:16 -07:00
7bbb53aaf8
Clang-tidy linting: make functions & global variables static
2025-10-28 11:39:16 -07:00
f44882aeeb
Enforce centralized dependency management; bump Gradle & deps versions
2025-10-28 11:39:16 -07:00
0ade7fb4d7
Polish binding: Remove verbose setup JNI APIs; Update state machine states.
2025-10-28 11:39:16 -07:00
7dc9968f82
Restructure `LLamaAndroid.kt`
2025-10-28 11:39:16 -07:00
44720859d6
Rewrite llama-android JNI implementation
2025-10-28 11:39:15 -07:00
d4ab3832cf
Use common sampler
2025-10-28 11:39:15 -07:00
1f255d4bca
Tidy & clean LLamaAndroid binding
2025-10-28 11:39:15 -07:00
56b4795842
model-conversion : add support for SentenceTransformers ( #16387 )
...
* model-conversion : add support for SentenceTransformers
This commit adds support for models that use SentenceTransformer layers.
The motivation for this is that if converted model includes any of the
numbered layers specified in the original models repository then these
changes enable these models to be used and verified. Currently the
model-conversion only support the base model output without any of
the additional transformation layers.
Usage:
Convert the model that also includes the SentenceTransformer layers:
```console
(venv) $ export EMBEDDING_MODEL_PATH="~/google/embeddinggemma-300M"
(venv) make embedding-convert-model
```
Verify the produced embeddings from the converted model against the
original model embeddings:
```console
(venv) make embedding-verify-logits-st
```
The original model can be run using SentenceTransformer:
```console
(venv) make embedding-run-original-model-st
```
Run the converted model using "SentenceTransformer" layers whic
enables pooling and normalization:
```console
(venv) make embedding-run-converted-model-st
```
* add model-conversion example requirements
* add support for -st flag in embedding model conversion
This commit add support for the -st flag in the embedding model
conversion script. This will enable models to be converted using
sentence transformers dense layers.
2025-10-09 14:35:22 +02:00
Han Yin
Daniel Bevenius