PEFT
Safetensors
Chinese
kev
queue-position
decision-model
lora
sft
permutation-consistency
chinese
Eval Results (legacy)
Instructions to use fzkun/kev-queue-v4-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use fzkun/kev-queue-v4-4b with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3.5-4B-Base") model = PeftModel.from_pretrained(base_model, "fzkun/kev-queue-v4-4b") - Notebooks
- Google Colab
- Kaggle
Download deployment/compose.queue.yaml from fzkun/kev-queue-v4-4b: direct link, hf CLI and curl.
- Browser
- Download file 468 Bytes
-
https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/deployment/compose.queue.yaml
- Command line
-
hf download hf://fzkun/kev-queue-v4-4b/deployment/compose.queue.yaml
-
curl -L -o compose.queue.yaml https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/deployment/compose.queue.yaml
468 Bytes
| services: | |
| kev: | |
| command: ["--run", "/queue-v4", "--fallback", "/queue-v4", "--host", "0.0.0.0", "--port", "8000"] | |
| environment: | |
| KEV_MERGE: "0" | |
| KEV_TEMPERATURE: "0.25" | |
| KEV_DEPLOY_MAX_STATE: "8192" | |
| KEV_PREFIX_MAX_TOKENS: "8192" | |
| KEV_GPU_MEMORY_FRACTION: "0.23" | |
| volumes: | |
| - ./queue-finetune/v4/results/experiment-v4b/queue-v4:/queue-v4:ro | |
| - ./queue-finetune/v4/deployment/service.queue.py:/opt/kev/service.deploy.py:ro | |