Feature Extraction
Transformers
TensorBoard
Safetensors
English
captionbert_v2
sentence-similarity
consensus-distillation
geometric-deep-learning
amoe
custom_code
Instructions to use AbstractPhil/captionbert-8192-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AbstractPhil/captionbert-8192-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AbstractPhil/captionbert-8192-v2", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AbstractPhil/captionbert-8192-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
stage1 alignment maps (maps)
Browse files- maps/alignment_maps.pt +3 -0
- maps/fit_report.json +72 -0
maps/alignment_maps.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ce7d282f6aeee9541900728b9cb93964ed6d49412550d28289ca333c915ca43
|
| 3 |
+
size 47225861
|
maps/fit_report.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bert": {
|
| 3 |
+
"in_sample": {
|
| 4 |
+
"cos": 1.0,
|
| 5 |
+
"r1": 0.9965000152587891,
|
| 6 |
+
"n": 24000,
|
| 7 |
+
"chance": 0.0005
|
| 8 |
+
},
|
| 9 |
+
"out_of_sample": {
|
| 10 |
+
"cos": 1.0,
|
| 11 |
+
"r1": 0.9909999966621399,
|
| 12 |
+
"n": 8000,
|
| 13 |
+
"chance": 0.0005
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"modern": {
|
| 17 |
+
"in_sample": {
|
| 18 |
+
"cos": 0.38715124130249023,
|
| 19 |
+
"r1": 0.9649999737739563,
|
| 20 |
+
"n": 24000,
|
| 21 |
+
"chance": 0.0005
|
| 22 |
+
},
|
| 23 |
+
"out_of_sample": {
|
| 24 |
+
"cos": 0.3266415596008301,
|
| 25 |
+
"r1": 0.9164999723434448,
|
| 26 |
+
"n": 8000,
|
| 27 |
+
"chance": 0.0005
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"roberta": {
|
| 31 |
+
"in_sample": {
|
| 32 |
+
"cos": 0.4255034923553467,
|
| 33 |
+
"r1": 0.9810000061988831,
|
| 34 |
+
"n": 24000,
|
| 35 |
+
"chance": 0.0005
|
| 36 |
+
},
|
| 37 |
+
"out_of_sample": {
|
| 38 |
+
"cos": 0.37222719192504883,
|
| 39 |
+
"r1": 0.9480000138282776,
|
| 40 |
+
"n": 8000,
|
| 41 |
+
"chance": 0.0005
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"albert": {
|
| 45 |
+
"in_sample": {
|
| 46 |
+
"cos": 0.3922822177410126,
|
| 47 |
+
"r1": 0.9785000085830688,
|
| 48 |
+
"n": 24000,
|
| 49 |
+
"chance": 0.0005
|
| 50 |
+
},
|
| 51 |
+
"out_of_sample": {
|
| 52 |
+
"cos": 0.3313330411911011,
|
| 53 |
+
"r1": 0.9384999871253967,
|
| 54 |
+
"n": 8000,
|
| 55 |
+
"chance": 0.0005
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"distil": {
|
| 59 |
+
"in_sample": {
|
| 60 |
+
"cos": 0.6433802247047424,
|
| 61 |
+
"r1": 0.9955000281333923,
|
| 62 |
+
"n": 24000,
|
| 63 |
+
"chance": 0.0005
|
| 64 |
+
},
|
| 65 |
+
"out_of_sample": {
|
| 66 |
+
"cos": 0.6245564818382263,
|
| 67 |
+
"r1": 0.9810000061988831,
|
| 68 |
+
"n": 8000,
|
| 69 |
+
"chance": 0.0005
|
| 70 |
+
}
|
| 71 |
+
}
|
| 72 |
+
}
|