Instructions to use Zichen1024/CoVe-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zichen1024/CoVe-4B with Transformers:

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

pipe = pipeline("text-generation", model="Zichen1024/CoVe-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Zichen1024/CoVe-4B")
model = AutoModelForCausalLM.from_pretrained("Zichen1024/CoVe-4B")
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 Zichen1024/CoVe-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zichen1024/CoVe-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zichen1024/CoVe-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zichen1024/CoVe-4B

SGLang

How to use Zichen1024/CoVe-4B 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 "Zichen1024/CoVe-4B" \
    --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": "Zichen1024/CoVe-4B",
		"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 "Zichen1024/CoVe-4B" \
        --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": "Zichen1024/CoVe-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zichen1024/CoVe-4B with Docker Model Runner:
```
docker model run hf.co/Zichen1024/CoVe-4B
```

CoVe-4B / README.md

nielsr HF Staff

Add library_name and base_model metadata

5718164 verified 3 months ago

3.03 kB

datasets:
  - Zichen1024/CoVe-12k
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
base_model: Qwen/Qwen3-4B-Instruct-2507
tags:
  - agent
  - tool-use

CoVe Mascot

📄 Paper | 🌐 Website | 🤗 Dataset |

Overview

CoVe-4B is a compact 4B interactive tool-use agent fine-tuned from Qwen3-4B-Instruct-2507 using the CoVe (Constraint-Verification) post-training framework. It is trained on CoVe-12K, a dataset of 12K high-quality multi-turn tool-use trajectories synthesized and verified by deterministic constraint checking.

The model was introduced in the paper CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification.

Framework

The CoVe framework. Explicit constraints are fuzzified to guide a User Simulator LLM, and original constraints act as a deterministic checklist to verify the agent's tool invocations.

Performance

Main Results Table
Main results on τ²-bench. CoVe-4B achieves top performance in the ≤8B group and rivals models up to 70B.

Deployment and Evaluation

CoVe-4B uses the Hermes tool-call format and can be deployed with vLLM.

Serve with vLLM

CUDA_VISIBLE_DEVICES=0,1,2,3 vllm serve [MODEL_HF_URL] \
  --served-model-name CoVe \
  --enable-auto-tool-choice \
  --tool-call-parser hermes \
  --tensor-parallel-size 1 \
  --data-parallel-size 4 \
  --host 0.0.0.0 \
  --port ${PORT}

Evaluate with τ²-bench

Once the model is running, evaluate using the official τ²-bench code. Set the agent model to the vLLM-served CoVe endpoint.

Citation

@article{Chen2026CoVe,
  title   = {CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification},
  author  = {Chen, Jinpeng and Gong, Cheng and Li, Hanbo and Liu, Ziru and Tian, Zichen and Fu, Xinyu and Wu, Shi and Zhang, Chenyang and Zhang, Wu and Zhang, Suiyun and Tu, Dandan and Liu, Rui},
  journal = {arXiv preprint arXiv:2603.01940},
  year    = {2026}
}