archives/edge-gallery
archives/edge-gallery
2
0
Fork 0
mirror of https://github.com/google-ai-edge/gallery.git synced 2025-07-16 11:16:43 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Add Hammer and Phi4 models

Browse source
This commit is contained in:
fat-tire 2025-05-21 23:28:41 -07:00 • committed by fattire
parent 734efab9d0
commit 8b0b99c860
1 changed files with 33 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

34
model_allowlist.json
View file

@ -61,7 +61,39 @@
"topK": 40,
"topP": 0.95,
"temperature": 1.0,
"maxTokens": 1024,
"maxTokens": 1280,
"accelerators": "gpu,cpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab"]
},
{
"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": "Hammer 2.1 model with strong function calling capability. These models are based on the Qwen 2.5 coder series and utilize function masking techniques and other advanced technologies. Hammer 2.1 series bring significant enhancements, while still maintaining the basic functionality of Hammer 2.0's Single-Turn interaction and further strengthening other capabilities.",
"sizeInBytes": 1625493432,
"version": "4e4a594e06ead9ad93e5a09a60eeea932561136cef0edd572d258144b42de6a2",
"defaultConfig": {
"topK": 40,
"topP": 0.95,
"temperature": 0.0,
"maxTokens": 1280,
"accelerators": "gpu,cpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab"]
},
{
"name": "Phi-4-mini-instruct q8",
"modelId": "litert-community/Phi-4-mini-instruct",
"modelFile": "Phi-4-mini-instruct_multi-prefill-seq_q8_ekv1280.task",
"description": "Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length.",
"sizeInBytes": 3944275882,
"version": "e494f9e827fbf47ac271d67dde77308f4a7683ad1ff630ab5bec926f17573b5f",
"defaultConfig": {
"topK": 40,
"topP": 0.95,
"temperature": 0.0,
"maxTokens": 1280,
"accelerators": "cpu"
},
"taskTypes": ["llm_chat", "llm_prompt_lab"]