Image-Text-to-Text
PEFT
Safetensors
English
muse_glimmer
trained-eye
qlora
lora
axolotl
smart-glasses
egocentric-vision
conversational
4-bit precision
bitsandbytes
Instructions to use amaan784/trained-eye with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use amaan784/trained-eye with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-models/Muse-Glimmer-30B") model = PeftModel.from_pretrained(base_model, "amaan784/trained-eye") - Notebooks
- Google Colab
- Kaggle
Trained Eye release product
Browse files- README.md +2 -1
- release.json +2 -2
README.md
CHANGED
|
@@ -184,7 +184,8 @@ or coaching, and anything where a missed or false alert could put someone at ris
|
|
| 184 |
- It watches only what the glasses can see: look away and it cannot tell whether the
|
| 185 |
condition is still true.
|
| 186 |
- If Muse Spark's check fails outright (an error, not a no), the alert is still spoken and
|
| 187 |
-
logged as unconfirmed
|
|
|
|
| 188 |
- The test labels were drafted by an AI assistant, too few events lasted past the hold to
|
| 189 |
judge alerts well, and Experiments 2 and 3 did not run.
|
| 190 |
- Validation during training was split by example, not by source frame, so related images
|
|
|
|
| 184 |
- It watches only what the glasses can see: look away and it cannot tell whether the
|
| 185 |
condition is still true.
|
| 186 |
- If Muse Spark's check fails outright (an error, not a no), the alert is still spoken and
|
| 187 |
+
logged as unconfirmed, on purpose, so a cloud outage never silences an alert; a no from
|
| 188 |
+
Spark holds it back.
|
| 189 |
- The test labels were drafted by an AI assistant, too few events lasted past the hold to
|
| 190 |
judge alerts well, and Experiments 2 and 3 did not run.
|
| 191 |
- Validation during training was split by example, not by source frame, so related images
|
release.json
CHANGED
|
@@ -11,8 +11,8 @@
|
|
| 11 |
},
|
| 12 |
{
|
| 13 |
"path": "README.md",
|
| 14 |
-
"bytes":
|
| 15 |
-
"sha256": "
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"path": "adapter_config.json",
|
|
|
|
| 11 |
},
|
| 12 |
{
|
| 13 |
"path": "README.md",
|
| 14 |
+
"bytes": 14345,
|
| 15 |
+
"sha256": "cb03f99a59924b4fa4526d0e64fbfa078e96c7b2999ab01850b0c16479a96106"
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"path": "adapter_config.json",
|