Instructions to use zkkk452/adaptive-env-selection-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zkkk452/adaptive-env-selection-checkpoint with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zkkk452/adaptive-env-selection-checkpoint")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("zkkk452/adaptive-env-selection-checkpoint", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zkkk452/adaptive-env-selection-checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zkkk452/adaptive-env-selection-checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zkkk452/adaptive-env-selection-checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zkkk452/adaptive-env-selection-checkpoint

SGLang

How to use zkkk452/adaptive-env-selection-checkpoint with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zkkk452/adaptive-env-selection-checkpoint" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zkkk452/adaptive-env-selection-checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zkkk452/adaptive-env-selection-checkpoint" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zkkk452/adaptive-env-selection-checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zkkk452/adaptive-env-selection-checkpoint with Docker Model Runner:
```
docker model run hf.co/zkkk452/adaptive-env-selection-checkpoint
```

Adaptive Env Selection Checkpoint Archive

This repository stores checkpoint artifacts for the course-project notebook in:

GitHub: https://github.com/kkkzzz0101/Adaptive-Env-Selection

Current contents:

nonrebucket_step200/global_step_200: raw training checkpoint for the Math+Zebra no-rebucket continuation run (80 -> 200)
rebucket_step100/global_step_100: raw training checkpoint for the Math+Zebra window-rebucket run (80 -> 200), preserved at step 100

Important note:

These uploads are preserved as raw global_step_* checkpoint directories.
They are useful for archival, recovery, and continuation.
They are not a clean one-folder Transformers inference export by themselves.
The notebook therefore treats Hugging Face checkpoint loading as optional and expects either a converted model directory or manual recovery from these raw checkpoints.

Related notebook behavior:

The deliverable notebook defaults to checked-in CSV/JSON/figure artifacts from the GitHub repository.
Optional checkpoint-based evaluation can reference this repository via AES_HF_MODEL_ID=zkkk452/adaptive-env-selection-checkpoint.

Downloads last month: -; Downloads are not tracked for this model. How to track