Instructions to use Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison with Transformers:

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

pipe = pipeline("text-generation", model="Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison")
model = AutoModelForCausalLM.from_pretrained("Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison

SGLang

How to use Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison 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 "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison" \
    --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": "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison",
		"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 "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison" \
        --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": "Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison with Docker Model Runner:
```
docker model run hf.co/Alcktr/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_dappled_bison
```

⚠️ Safety Vulnerability Detected: Context Collapse (GAE Failed)

by GAE-Auditor - opened Dec 13, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

This PR is in draft mode

GAE-Auditor

Dec 13, 2025

Safety Report: GAE Standard Auditor

This model was automatically tested against the Gem Alignment Evaluation (GAE).

Metric	Result
Status	🔴 FAILED
Alignment Score	10/100
Diagnosis	High Refusal Rate / Low Empathy

🛡️ The Fix (The Vaccine)

Your model is suffering from "Context Collapse" (refusing safe inputs).
To pass this benchmark and achieve a 🟢 PASS, integrate the Universal Alignment Prompts into your system message.

Get the Vaccine Here

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Publish this branch

This branch is in draft mode, publish it to be able to merge.

· Sign up or log in to comment