Feature Extraction
sentence-transformers
Safetensors
code
bert
code-search
code-retrieval
text-embeddings-inference
Instructions to use thinkingdbx/codebert-permissive-embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use thinkingdbx/codebert-permissive-embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("thinkingdbx/codebert-permissive-embed") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Remove internal artifact LINEAGE.md
Browse files- LINEAGE.md +0 -27
LINEAGE.md
DELETED
|
@@ -1,27 +0,0 @@
|
|
| 1 |
-
# Lineage — CODEBERT_EMBED_V2-8f13d02d
|
| 2 |
-
|
| 3 |
-
What went in, what was done to it, and what came out.
|
| 4 |
-
|
| 5 |
-
## Sources
|
| 6 |
-
|
| 7 |
-
- **code_pairs_fn** (files) `/home/ubuntu/data/code_pairs_fn.jsonl`, **not pinned to a version**
|
| 8 |
-
|
| 9 |
-
## Preparation applied
|
| 10 |
-
|
| 11 |
-
- PII redaction: not applied
|
| 12 |
-
- Decontamination: no evaluation sets declared
|
| 13 |
-
|
| 14 |
-
## Stages
|
| 15 |
-
|
| 16 |
-
| stage | status | detail |
|
| 17 |
-
| --- | --- | --- |
|
| 18 |
-
| precheck | passed | all checks passed |
|
| 19 |
-
| corpus | passed | 1 warn |
|
| 20 |
-
| tokenizer | skipped | plan=reuse, using an existing tokenizer |
|
| 21 |
-
| train | passed | loss 0.5576 over 1673 steps, R@1 0.764, MRR 0.813 |
|
| 22 |
-
| merge | skipped | method=full, nothing to merge |
|
| 23 |
-
| eval | skipped | only 0 held-out documents; too few to measure retrieval against a realistic haystack |
|
| 24 |
-
| validate | passed | 1 warn |
|
| 25 |
-
| serve_smoke | passed | 8 probes embedded to 768 dimensions, 2.5 ms/text, unrelated texts at cosine 0.054 |
|
| 26 |
-
|
| 27 |
-
Spec digest `sha256:8f13d02db956b9db40326791fef0b1269417403422b298df43a80bb7ac072be6`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|