Instructions to use PanzerBread/PromptCoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PanzerBread/PromptCoT with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "PanzerBread/PromptCoT")

Transformers

How to use PanzerBread/PromptCoT with Transformers:

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

pipe = pipeline("text-generation", model="PanzerBread/PromptCoT")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PanzerBread/PromptCoT", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PanzerBread/PromptCoT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PanzerBread/PromptCoT

SGLang

How to use PanzerBread/PromptCoT 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 "PanzerBread/PromptCoT" \
    --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": "PanzerBread/PromptCoT",
		"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 "PanzerBread/PromptCoT" \
        --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": "PanzerBread/PromptCoT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use PanzerBread/PromptCoT with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PanzerBread/PromptCoT to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PanzerBread/PromptCoT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PanzerBread/PromptCoT to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="PanzerBread/PromptCoT",
    max_seq_length=2048,
)

Docker Model Runner
How to use PanzerBread/PromptCoT with Docker Model Runner:
```
docker model run hf.co/PanzerBread/PromptCoT
```

PanzerBread commited on Nov 16, 2025

Commit

ad5ae36

verified ·

1 Parent(s): 8278bb4

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -62,8 +62,8 @@ model = PeftModel.from_pretrained(base_model, "PanzerBread/promptcot-p")
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
 concepts = "algebra | quadratic equations"
-rationale = "We need to find the roots of a quadratic equation..."
-prompt = f"Concepts: {concepts}\nRationale: {rationale}\nProblem:"
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(**inputs, max_new_tokens=256)

 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
 concepts = "algebra | quadratic equations"
+# It will think about the concepts, and then generate a problem after "Problem: "
+prompt = f"Concepts: {concepts}\nRationale:"
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(**inputs, max_new_tokens=256)