Sentence Similarity
sentence-transformers
Safetensors
mamba2
feature-extraction
vertical-chunking
custom_code
Instructions to use dynatrace-oss/llama-embed-mamba2-1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use dynatrace-oss/llama-embed-mamba2-1.3b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("dynatrace-oss/llama-embed-mamba2-1.3b", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
chore: update integration roadmap
Browse files
README.md
CHANGED
|
@@ -148,10 +148,9 @@ Our goal is to integrate all necessary changes to simplify the adoption of verti
|
|
| 148 |
> [!Note]
|
| 149 |
> ⚪ Planned | 🟡 In Progress | 🟢 Integrated
|
| 150 |
|
| 151 |
-
- ⚪ **
|
| 152 |
-
- ⚪ **
|
| 153 |
-
- ⚪ **
|
| 154 |
-
- ⚪ **transformers:** Use updated `mamba_split_conv1d_scan_combined` with cache params during inference (currently only used during training, not configurable, problems with left padding)
|
| 155 |
- ⚪ **sentence-transformers:** Native vertical chunking support
|
| 156 |
|
| 157 |
*This list will be updated as integration progresses.*
|
|
|
|
| 148 |
> [!Note]
|
| 149 |
> ⚪ Planned | 🟡 In Progress | 🟢 Integrated
|
| 150 |
|
| 151 |
+
- ⚪ **mamba-ssm:** Use `initial_states` in `mamba_split_conv1d_scan_combined` and export final states
|
| 152 |
+
- ⚪ **kernels-community:** Propagate changes in `mamba-ssm` to its kernel hub equivalent in the `kernels-community` repository
|
| 153 |
+
- ⚪ **transformers:** Use updated `mamba_split_conv1d_scan_combined` with cache params during inference (currently only used during training, not configurable, problems with cache)
|
|
|
|
| 154 |
- ⚪ **sentence-transformers:** Native vertical chunking support
|
| 155 |
|
| 156 |
*This list will be updated as integration progresses.*
|