Instructions to use ajinkyamulay/iolai-qwen3-14b-awq-push with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajinkyamulay/iolai-qwen3-14b-awq-push with Transformers:

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

pipe = pipeline("text-generation", model="ajinkyamulay/iolai-qwen3-14b-awq-push")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ajinkyamulay/iolai-qwen3-14b-awq-push", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajinkyamulay/iolai-qwen3-14b-awq-push with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajinkyamulay/iolai-qwen3-14b-awq-push"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajinkyamulay/iolai-qwen3-14b-awq-push",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ajinkyamulay/iolai-qwen3-14b-awq-push

SGLang

How to use ajinkyamulay/iolai-qwen3-14b-awq-push 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 "ajinkyamulay/iolai-qwen3-14b-awq-push" \
    --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": "ajinkyamulay/iolai-qwen3-14b-awq-push",
		"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 "ajinkyamulay/iolai-qwen3-14b-awq-push" \
        --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": "ajinkyamulay/iolai-qwen3-14b-awq-push",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ajinkyamulay/iolai-qwen3-14b-awq-push with Docker Model Runner:
```
docker model run hf.co/ajinkyamulay/iolai-qwen3-14b-awq-push
```

IOL-AI 2026 — Qwen3-14B-AWQ bounded thinking

Controlled follow-up to the preserved rank1-0.1470 non-thinking submission.

The script first generates the exact greedy, non-thinking baseline for every problem and atomically checkpoints a complete submission. It then attempts one bounded Qwen3 thinking generation per problem using the official sampling settings (temperature=0.6, top_p=0.95, top_k=20) and a stable per-row seed. A baseline answer is replaced only when generation:

ends naturally at EOS;
contains Qwen3's </think> token (151668);
has a non-empty final suffix after the last close token; and
returns the same number of answer lines as the baseline.

Incomplete, timed-out, malformed, or failed thoughts retain the proven direct answer. Each thinking call is capped at 1,536 tokens and at most 120 seconds, with a global soft deadline 150 seconds below the evaluator's 30-minute limit.

The repository remains fully offline and reuses the pinned local model and the bundled Transformers 4.51.3 / AutoAWQ 0.2.9 runtime.

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

Model tree for ajinkyamulay/iolai-qwen3-14b-awq-push

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

Qwen/Qwen3-14B-AWQ

Finetuned

(3)

this model