archives/edge-gallery
archives/edge-gallery
2
0
Fork 0
mirror of https://github.com/google-ai-edge/gallery.git synced 2025-07-08 07:30:35 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Create model_allowlist.json

Browse source
This commit is contained in:
Jing Jin 2025-05-17 15:07:15 -07:00 • committed by GitHub
parent bedc488a15
commit 6aa6c751bd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 49 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

49
model_allowlist.json Normal file
View file

@ -0,0 +1,49 @@
{
"models": [
{
"name": "Gemma3-1B-IT q4",
"modelId": "litert-community/Gemma3-1B-IT",
"modelFile": "Gemma3-1B-IT_multi-prefill-seq_q4_ekv2048.task",
"description": "A variant of [google/Gemma-3-1B-IT](https://huggingface.co/google/Gemma-3-1B-IT) with 4-bit quantization ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference)",
"sizeInBytes": 554661246,
"version": "20250514",
"defaultConfig": {
"topK": 64,
"topP": 0.95,
"temperature": 1.0,
"accelerators": "cpu,gpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab", "llm_usecases"]
},
{
"name": "Hammer2.1-1.5b q8",
"modelId": "litert-community/Hammer2.1-1.5b",
"modelFile": "Hammer2.1-1.5b_multi-prefill-seq_q8_ekv1280.task",
"description": "A variant of [MadeAgents/Hammer2.1-1.5b](https://huggingface.co/MadeAgents/Hammer2.1-1.5b) with 8-bit quantization ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference)",
"sizeInBytes": 1617946305,
"version": "20250514",
"defaultConfig": {
"topK": 40,
"topP": 0.95,
"temperature": 1.0,
"accelerators": "cpu,gpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab", "llm_usecases"]
},
{
"name": "Qwen2.5-1.5B-Instruct q8",
"modelId": "litert-community/Qwen2.5-1.5B-Instruct",
"modelFile": "Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv1280.task",
"description": "A variant of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) with 8-bit quantization ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference)",
"sizeInBytes": 1625493432,
"version": "20250514",
"defaultConfig": {
"topK": 40,
"topP": 0.95,
"temperature": 1.0,
"accelerators": "cpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab", "llm_usecases"]
}
]
}