My-Model-7B-DARE
What is this?
Merged model using DARE method combining coding + reasoning checkpoints.
Benchmark Results
| Task | Score |
|---|---|
| MMLU | 27.72 |
| HellaSwag | 40.00 |
| ARC-Challenge | 0.00 |
| ARC-Easy | 20.00 |
How to use
from transformers import pipeline
pipe = pipeline("text-generation", model="your-username/your-model")
print(pipe("Your prompt here")[0]['generated_text'])
Training Details
- Merge method: DARE
- Base models: checkpoint-A (coding) + checkpoint-B (reasoning)
- Merge tool: mergekit
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support