Text Generation
PEFT
Safetensors
English
lora
qlora
agentic-swe
agent-supervision
recovery-controller
tool-use
structured-output
conversational
Instructions to use usedot/Dot-Reflex-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use usedot/Dot-Reflex-14B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B-Base") model = PeftModel.from_pretrained(base_model, "usedot/Dot-Reflex-14B") - Notebooks
- Google Colab
- Kaggle
Download examples/trajectory_false_completion.json from usedot/Dot-Reflex-14B: direct link, hf CLI and curl.
- Browser
- Download file 621 Bytes
-
https://huggingface.co/usedot/Dot-Reflex-14B/resolve/main/examples/trajectory_false_completion.json
- Command line
-
hf download hf://usedot/Dot-Reflex-14B/examples/trajectory_false_completion.json
-
curl -L -o trajectory_false_completion.json https://huggingface.co/usedot/Dot-Reflex-14B/resolve/main/examples/trajectory_false_completion.json
621 Bytes
| { | |
| "task_summary": "Add password-reset token validation", | |
| "execution_history": [ | |
| { | |
| "step": 1, | |
| "actor": "agent", | |
| "action": "Modified auth/reset.py and declared the task complete.", | |
| "result": "The patch applied cleanly, but no verification command was run." | |
| } | |
| ], | |
| "tool_results": [ | |
| { | |
| "tool": "pytest", | |
| "status": "not_run", | |
| "summary": "Tests were never executed." | |
| } | |
| ], | |
| "current_state": "Code was changed, but there is no evidence that token validation works.", | |
| "detected_failure_signals": [ | |
| "false_completion_risk", | |
| "missing_verification" | |
| ] | |
| } | |