Text Classification
Transformers
English
Indonesian
code
security
code-review
static-analysis
vulnerability-detection
sarif
sliding-window-attention
spark
cpp
avx2
awq
experimental
Instructions to use wxsys/spark-servitor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wxsys/spark-servitor with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="wxsys/spark-servitor")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wxsys/spark-servitor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download servitor_config.json from wxsys/spark-servitor: direct link, hf CLI and curl.
- Browser
- Download file 732 Bytes
-
https://huggingface.co/wxsys/spark-servitor/resolve/main/servitor_config.json
- Command line
-
hf download hf://wxsys/spark-servitor/servitor_config.json
-
curl -L -o servitor_config.json https://huggingface.co/wxsys/spark-servitor/resolve/main/servitor_config.json
732 Bytes
| { | |
| "vocab_size": 151936, | |
| "hidden_size": 2048, | |
| "intermediate_size": 6656, | |
| "num_hidden_layers": 28, | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 2, | |
| "head_dim": 128, | |
| "sliding_window": 512, | |
| "full_attn_layers": [ | |
| 3, | |
| 7, | |
| 11, | |
| 15, | |
| 19, | |
| 23, | |
| 27 | |
| ], | |
| "use_hysparse2": true, | |
| "hysparse2_anchors": [ | |
| 3, | |
| 15 | |
| ], | |
| "enable_file_soft_reset": true, | |
| "file_soft_reset_alpha": 0.2, | |
| "max_position_embeddings": 1048576, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta_swa": 10000.0, | |
| "rope_theta_full": 5000000.0, | |
| "has_output_gate": true, | |
| "num_verdicts": 3, | |
| "num_pathologies": 10, | |
| "dual_exit_layer": 14, | |
| "enable_pondering": true, | |
| "max_ponder_cycles": 4, | |
| "ponder_halt_threshold": 0.95 | |
| } |