Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
ivanfioravanti
/
d1-2B-gestures-CoreAI
Like
1
Image-Text-to-Text
liquid
lfm3
d1
decision-model
core-ai
apple-neural-engine
apple-silicon
macos
License:
lfm1.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
d1-2B-gestures-CoreAI
17.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
12 commits
ivanfioravanti
Prompt as inputs (no baked questions), split Neural Engine model for iOS, card and code
7011ac6
verified
3 days ago
code
Prompt as inputs (no baked questions), split Neural Engine model for iOS, card and code
3 days ago
d1_ane_fp16.aimodel
d1_ane_fp16.aimodel: MLPs in 8 chunks, 1.4x faster on the Neural Engine (236 -> 171 ms)
3 days ago
d1_ane_prompt_fp16.aimodel
d1_ane_prompt_fp16: Neural Engine layout, the questions as inputs
3 days ago
d1_ane_prompt_split_fp16
d1_ane_prompt_split_fp16: the Neural Engine export in 4 pieces (iOS's Neural Engine compiler can't take 3.1 GB at once), questions as inputs
3 days ago
d1_gpu_fp16.aimodel
d1_gpu_fp16.aimodel: GPU, fp16
3 days ago
d1_gpu_prompt_fp16.aimodel
d1_gpu_prompt_fp16: the questions as inputs (prompt padded to 640 tokens)
3 days ago
.gitattributes
Safe
2.15 kB
d1_ane_prompt_split_fp16: the Neural Engine export in 4 pieces (iOS's Neural Engine compiler can't take 3.1 GB at once), questions as inputs
3 days ago
LICENSE
Safe
10.6 kB
Card, LFM Open License v1.0, calibration, prompt and code
3 days ago
README.md
Safe
8.06 kB
Prompt as inputs (no baked questions), split Neural Engine model for iOS, card and code
3 days ago
calibration.json
Safe
4.92 kB
Card, LFM Open License v1.0, calibration, prompt and code
3 days ago
embed_tokens_fp16.npy
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
524 MB
xet
embed_tokens_fp16.npy: d1-2B's input embeddings, to build the prompt inputs
3 days ago
prompt.json
Safe
69.7 kB
Card, LFM Open License v1.0, calibration, prompt and code
3 days ago