Instructions to use thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored")
model = AutoModelForCausalLM.from_pretrained("thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored

SGLang

How to use thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored 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 "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored with Docker Model Runner:
```
docker model run hf.co/thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored
```

it needs a stronger uncensor

by zekses - opened Nov 26, 2024

Discussion

zekses

Nov 26, 2024

This comment has been hidden

sloshywings

thirdeye Ai org Nov 26, 2024

can you post what the exact phrasing of the refusal you got was?

zekses

Nov 26, 2024

This comment has been hidden

sloshywings

thirdeye Ai org Nov 26, 2024

•

edited Nov 26, 2024

yeah, we are happy with the minimal censors that the model contains. the model is mainly for uncensored programming responses; i.e. programming tasks where the ordinary qwen2.5 coder would provide a refusal such as opsec tasks and whitehat hacking.

vpakarinen

Jan 28, 2025

I agree, this is not really uncensored that much.

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

Tap or paste here to upload images

· Sign up or log in to comment