Text Classification
PEFT
Safetensors
English
Korean
rlcd
system-1
non-autoregressive
decision-model
reward-model
llm-judge
calibrated-decisions
kev
qwen3.5
reinforcement-learning
fast-inference
ultra-low-latency
Instructions to use gyung/Qwev-9B-RLCD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use gyung/Qwev-9B-RLCD with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3.5-9B-Base") model = PeftModel.from_pretrained(base_model, "gyung/Qwev-9B-RLCD") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,6 @@ language:
|
|
| 22 |
datasets:
|
| 23 |
- allenai/reward-bench
|
| 24 |
- pminervini/HaluEval
|
| 25 |
-
- TIGER-Lab/MMLU-Pro
|
| 26 |
- THU-KEG/RM-Bench
|
| 27 |
- LocalLLaMA/typed-decisions
|
| 28 |
metrics:
|
|
@@ -317,4 +316,4 @@ def route_decision(model, tok, record, tau=0.90):
|
|
| 317 |
publisher={Hugging Face},
|
| 318 |
howpublished={\url{https://huggingface.co/gyung/Qwev-9B-RLCD}}
|
| 319 |
}
|
| 320 |
-
```
|
|
|
|
| 22 |
datasets:
|
| 23 |
- allenai/reward-bench
|
| 24 |
- pminervini/HaluEval
|
|
|
|
| 25 |
- THU-KEG/RM-Bench
|
| 26 |
- LocalLLaMA/typed-decisions
|
| 27 |
metrics:
|
|
|
|
| 316 |
publisher={Hugging Face},
|
| 317 |
howpublished={\url{https://huggingface.co/gyung/Qwev-9B-RLCD}}
|
| 318 |
}
|
| 319 |
+
```
|