Instructions to use cesun/ThinkEdit-deepseek-qwen-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cesun/ThinkEdit-deepseek-qwen-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="cesun/ThinkEdit-deepseek-qwen-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cesun/ThinkEdit-deepseek-qwen-1.5b")
model = AutoModelForCausalLM.from_pretrained("cesun/ThinkEdit-deepseek-qwen-1.5b", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cesun/ThinkEdit-deepseek-qwen-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cesun/ThinkEdit-deepseek-qwen-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cesun/ThinkEdit-deepseek-qwen-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cesun/ThinkEdit-deepseek-qwen-1.5b

SGLang

How to use cesun/ThinkEdit-deepseek-qwen-1.5b 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 "cesun/ThinkEdit-deepseek-qwen-1.5b" \
    --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": "cesun/ThinkEdit-deepseek-qwen-1.5b",
		"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 "cesun/ThinkEdit-deepseek-qwen-1.5b" \
        --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": "cesun/ThinkEdit-deepseek-qwen-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cesun/ThinkEdit-deepseek-qwen-1.5b with Docker Model Runner:
```
docker model run hf.co/cesun/ThinkEdit-deepseek-qwen-1.5b
```

Add text-generation pipeline tag, link to code and license

by nielsr HF Staff - opened Apr 12, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -1,7 +1,10 @@
 ---
 library_name: transformers
 tags: []
 ---
 **Repository for:**
 **ThinkEdit-deepseek-qwen-1.5b**
@@ -11,6 +14,8 @@ tags: []
 **Authors**: Chung-En Sun, Ge Yan, Tsui-Wei Weng\
 **Paper**: [ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models](https://arxiv.org/abs/2503.22048)
 ---
 ## Introduction
@@ -19,8 +24,8 @@ Reasoning-augmented models sometimes fail by generating **overly short**, abstra
 **ThinkEdit** is a lightweight weight-editing method that:
-- Identifies \~2% of "short reasoning" attention heads
-- Edits only \~0.1% of total parameters
 - Removes the "short reasoning" direction from their output
 - Boosts performance, especially on cases with short reasoning traces

 ---
 library_name: transformers
 tags: []
+pipeline_tag: text-generation
+license: mit
 ---
 **Repository for:**
 **ThinkEdit-deepseek-qwen-1.5b**
 **Authors**: Chung-En Sun, Ge Yan, Tsui-Wei Weng\
 **Paper**: [ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models](https://arxiv.org/abs/2503.22048)
+Github: https://github.com/Trustworthy-ML-Lab/ThinkEdit
 ---
 ## Introduction
 **ThinkEdit** is a lightweight weight-editing method that:
+- Identifies ~2% of "short reasoning" attention heads
+- Edits only ~0.1% of total parameters
 - Removes the "short reasoning" direction from their output
 - Boosts performance, especially on cases with short reasoning traces