Feature Extraction
Transformers
TensorBoard
Safetensors
English
captionbert_structured_rotary
sentence-similarity
consensus-distillation
rotary-embeddings
custom_code
Instructions to use AbstractPhil/captionbert-8192-rotary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AbstractPhil/captionbert-8192-rotary with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AbstractPhil/captionbert-8192-rotary", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AbstractPhil/captionbert-8192-rotary", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ship H16-seed1 (all arms retained)
Browse files- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/best.safetensors +1 -1
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/eval-004500.json +16 -0
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/eval-005000.json +16 -0
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/resume.json +1 -1
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/state.pt +1 -1
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/tensorboard/events.out.tfevents.1793984194.79fe39615b31.56708.0 +2 -2
- experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/train.jsonl +0 -0
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/best.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 216583564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9de26c49cb525fa081f49144366780799d9ca008e54433202f95b9211c3c6bd6
|
| 3 |
size 216583564
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/eval-004500.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"above_128_tokens": {
|
| 3 |
+
"cos_to_target": 0.73018479347229,
|
| 4 |
+
"erank": 71.62114543420721,
|
| 5 |
+
"n": 5000,
|
| 6 |
+
"self_cos": 0.009640409377365594
|
| 7 |
+
},
|
| 8 |
+
"above_128_total_rows": 29240,
|
| 9 |
+
"heldout": {
|
| 10 |
+
"cos_to_target": 0.8011217713356018,
|
| 11 |
+
"erank": 94.19025130946667,
|
| 12 |
+
"n": 5000,
|
| 13 |
+
"self_cos": 0.0045877611036949165
|
| 14 |
+
},
|
| 15 |
+
"heldout_total_rows": 500000
|
| 16 |
+
}
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/eval-005000.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"above_128_tokens": {
|
| 3 |
+
"cos_to_target": 0.7263261079788208,
|
| 4 |
+
"erank": 73.34710769279435,
|
| 5 |
+
"n": 5000,
|
| 6 |
+
"self_cos": 0.022493096191054805
|
| 7 |
+
},
|
| 8 |
+
"above_128_total_rows": 29240,
|
| 9 |
+
"heldout": {
|
| 10 |
+
"cos_to_target": 0.8050075173377991,
|
| 11 |
+
"erank": 94.64550368351088,
|
| 12 |
+
"n": 5000,
|
| 13 |
+
"self_cos": 0.005167805371121394
|
| 14 |
+
},
|
| 15 |
+
"heldout_total_rows": 500000
|
| 16 |
+
}
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/resume.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"config_id": "aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e",
|
| 4 |
"dataset_id": "7adb10f8833fab44e3ebb44315b53cb65bd8010b038115d15350b18536b57e86",
|
| 5 |
"seed": 1,
|
| 6 |
-
"step":
|
| 7 |
}
|
|
|
|
| 3 |
"config_id": "aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e",
|
| 4 |
"dataset_id": "7adb10f8833fab44e3ebb44315b53cb65bd8010b038115d15350b18536b57e86",
|
| 5 |
"seed": 1,
|
| 6 |
+
"step": 5300
|
| 7 |
}
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/state.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 649784662
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c20d0e35b4ed059a6f73b3339aacacfa4bd00501512d29c2530d2a9d0fcc129a
|
| 3 |
size 649784662
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/tensorboard/events.out.tfevents.1793984194.79fe39615b31.56708.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0872aec861095c231f245f29bde6fa4fd358763ee58a5708681a976705c10723
|
| 3 |
+
size 3406415
|
experiments/aafe9c59b9d696107cb4393f3a26815e84714daddb7d6eb028b5d6137b88418e/H16-seed1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|