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/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/best.safetensors +1 -1
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-004000.json +16 -0
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-004500.json +16 -0
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-005000.json +16 -0
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/resume.json +1 -1
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/state.pt +1 -1
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/tensorboard/events.out.tfevents.1793991823.79fe39615b31.56708.2 +2 -2
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/train.jsonl +0 -0
- experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/trajectory-mid.safetensors +3 -0
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/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 sha256:787d2e6cf9845fdf3bb5a5905acb79fa02f3ffd45373eb40904736d25aa75781
|
| 3 |
size 216583564
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-004000.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"above_128_tokens": {
|
| 3 |
+
"cos_to_target": 0.7160316109657288,
|
| 4 |
+
"erank": 68.76624029717973,
|
| 5 |
+
"n": 5000,
|
| 6 |
+
"self_cos": 0.021030287425943404
|
| 7 |
+
},
|
| 8 |
+
"above_128_total_rows": 29240,
|
| 9 |
+
"heldout": {
|
| 10 |
+
"cos_to_target": 0.7895890474319458,
|
| 11 |
+
"erank": 91.93690202949963,
|
| 12 |
+
"n": 5000,
|
| 13 |
+
"self_cos": 0.011685357192818482
|
| 14 |
+
},
|
| 15 |
+
"heldout_total_rows": 500000
|
| 16 |
+
}
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-004500.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"above_128_tokens": {
|
| 3 |
+
"cos_to_target": 0.7317603826522827,
|
| 4 |
+
"erank": 68.6062452275063,
|
| 5 |
+
"n": 5000,
|
| 6 |
+
"self_cos": 0.015403763021290222
|
| 7 |
+
},
|
| 8 |
+
"above_128_total_rows": 29240,
|
| 9 |
+
"heldout": {
|
| 10 |
+
"cos_to_target": 0.8015243411064148,
|
| 11 |
+
"erank": 91.1582994158243,
|
| 12 |
+
"n": 5000,
|
| 13 |
+
"self_cos": 0.004842295973423665
|
| 14 |
+
},
|
| 15 |
+
"heldout_total_rows": 500000
|
| 16 |
+
}
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/eval-005000.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"above_128_tokens": {
|
| 3 |
+
"cos_to_target": 0.7341196537017822,
|
| 4 |
+
"erank": 69.90356928562832,
|
| 5 |
+
"n": 5000,
|
| 6 |
+
"self_cos": 0.012606811987270001
|
| 7 |
+
},
|
| 8 |
+
"above_128_total_rows": 29240,
|
| 9 |
+
"heldout": {
|
| 10 |
+
"cos_to_target": 0.8010330200195312,
|
| 11 |
+
"erank": 93.12569682947488,
|
| 12 |
+
"n": 5000,
|
| 13 |
+
"self_cos": 0.004509944352612126
|
| 14 |
+
},
|
| 15 |
+
"heldout_total_rows": 500000
|
| 16 |
+
}
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/resume.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"config_id": "fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e",
|
| 4 |
"dataset_id": "659b21c1c6eb1074eeec7acdbfa9bd010965595a4669338690cf3ae38a4448d5",
|
| 5 |
"seed": 1,
|
| 6 |
-
"step":
|
| 7 |
}
|
|
|
|
| 3 |
"config_id": "fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e",
|
| 4 |
"dataset_id": "659b21c1c6eb1074eeec7acdbfa9bd010965595a4669338690cf3ae38a4448d5",
|
| 5 |
"seed": 1,
|
| 6 |
+
"step": 5100
|
| 7 |
}
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/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:d4d1f3c962946f048618242a6b77eb47fe83d1e11defade647c01438f4e5e2e5
|
| 3 |
size 649784662
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/tensorboard/events.out.tfevents.1793991823.79fe39615b31.56708.2
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 sha256:02549bd57469b0a9c54106fb6950fc79269034daa286bdbed0e6e3b29ec61042
|
| 3 |
+
size 3278095
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
experiments/fad07b2a05857a7abef278004986cacc1e3b8eb89b70943668505ea90498525e/H16-seed1/trajectory-mid.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90176b6f37c711924512f52fa036dc50389940d06ae41ab77b93aacec0c7e75b
|
| 3 |
+
size 216583564
|