Text Classification
Transformers
Safetensors
English
mistral3
image-text-to-text
decision-model
typed-decisions
schema-head
jev
calibration
decode-free
Instructions to use StandardThinking/StandardOne-3B-SH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StandardThinking/StandardOne-3B-SH with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="StandardThinking/StandardOne-3B-SH")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("StandardThinking/StandardOne-3B-SH") model = AutoModelForMultimodalLM.from_pretrained("StandardThinking/StandardOne-3B-SH", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update weights (v4)
Browse files
head/schema_head.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 278062780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d76a712bf7908d3d7d7d9f581817147ea8296bf2f4746db5022ba00936424448
|
| 3 |
size 278062780
|
head/schema_head_config.json
CHANGED
|
@@ -1,30 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"taps": [
|
| 16 |
-
|
| 17 |
-
|
| 18 |
],
|
| 19 |
-
"template": "schema-v1"
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
"
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
"template": "schema-v1-nosys",
|
| 26 |
-
"step": 1113,
|
| 27 |
-
"lora_rank": 64,
|
| 28 |
-
"snapshot": "/scratch/schema-head/models/StandardOne-3B-SH",
|
| 29 |
-
"preview": true
|
| 30 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"head": {
|
| 3 |
+
"hidden_size": 3072,
|
| 4 |
+
"n_taps": 2,
|
| 5 |
+
"d": 1024,
|
| 6 |
+
"heads": 16,
|
| 7 |
+
"ffn": 2816,
|
| 8 |
+
"route_blocks": 2,
|
| 9 |
+
"interact_blocks": 2,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"n_roles": 5,
|
| 12 |
+
"ord_hidden": 256,
|
| 13 |
+
"max_nodes": 4096,
|
| 14 |
+
"grad_checkpoint": true,
|
| 15 |
+
"taps": [
|
| 16 |
+
"final",
|
| 17 |
+
19
|
| 18 |
+
],
|
| 19 |
+
"template": "schema-v1"
|
| 20 |
+
},
|
| 21 |
"taps": [
|
| 22 |
+
"final",
|
| 23 |
+
19
|
| 24 |
],
|
| 25 |
+
"template": "schema-v1-nosys",
|
| 26 |
+
"step": 11471,
|
| 27 |
+
"lora_rank": 64,
|
| 28 |
+
"snapshot": "StandardOne-3B-SH@v3",
|
| 29 |
+
"preview": true
|
| 30 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4995664864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aca88073d0254fbd02507b8e0200f47cc254fb99aa3a7d4d6a3d08c918c50389
|
| 3 |
size 4995664864
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2702576200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbe1c06515b88895596fcad1745959681bbd1e29bf41137d9c2f115c2e563471
|
| 3 |
size 2702576200
|