curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/OpenIntelligenceNet%2FSpark-X2.5-1.7B-Uncensored" No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.
What is a refusal direction? →This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.
| model.safetensors | 3.18 GB | c4be5e72 | download |
| tokenizer.json | 9.65 MB | 2591c719 | download |
| tokenizer_config.json | 20.3 KB | 64bea0dc | download |
| modeling_spark.py | 19.0 KB | 4e48c7a9 | download |
| chat_template.jinja | 4.54 KB | 6c6617ee | download |
| configuration_spark.py | 4.23 KB | cca611a0 | download |
| config.json | 1.79 KB | d243c3b8 | download |
| .gitattributes | 1.48 KB | a6344aac | download |
| special_tokens_map.json | 613 B | 98515315 | download |
| README.md | 521 B | d6d7256d | download |
| generation_config.json | 231 B | 815d3009 | download |
license: apache-2.0
base_model: XHToken/Spark-X2.5-1.7B
tags:
OpenIntelligenceNet/Spark-X2.5-1.7B-Uncensored is a merged, full-precision fine-tuned version of XHToken/Spark-X2.5-1.7B.
The model was fine-tuned using a curated dataset of 60,000 uncensored examples to remove refusal behaviors and standard alignment restrictions, allowing direct and objective responses to sensitive queries.
Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.