Instructions to use future7/CogniDet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use future7/CogniDet with Transformers:

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

pipe = pipeline("text-generation", model="future7/CogniDet")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("future7/CogniDet")
model = AutoModelForCausalLM.from_pretrained("future7/CogniDet")
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 future7/CogniDet with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "future7/CogniDet"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "future7/CogniDet",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/future7/CogniDet

SGLang

How to use future7/CogniDet 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 "future7/CogniDet" \
    --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": "future7/CogniDet",
		"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 "future7/CogniDet" \
        --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": "future7/CogniDet",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use future7/CogniDet with Docker Model Runner:
```
docker model run hf.co/future7/CogniDet
```

future7

nielsr HF Staff commited on Jun 28, 2025

Commit

f9d0bf8

verified ·

1 Parent(s): fa3a3c1

Improve model card: Add paper link and refine description (#2)

Browse files

- Improve model card: Add paper link and refine description (2c8c0ba506f7c5576909d1fd19627d656b496a91)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +11 -10

README.md CHANGED Viewed

@@ -1,4 +1,11 @@
 ---
 library_name: transformers
 pipeline_tag: text-generation
 tags:
@@ -7,19 +14,11 @@ tags:
 - RAG evaluation
 - cognitive statements
 - factual consistency
-datasets:
-- future7/CogniBench
-- future7/CogniBench-L
-language:
-- en
-base_model:
-- meta-llama/Meta-Llama-3-8B
 ---
 # CogniDet: Cognitive Faithfulness Detector for LLMs
-**CogniDet** is a state-of-the-art model for detecting **both factual and cognitive hallucinations** in Large Language Model (LLM) outputs. Developed as part of the [CogniBench](https://github.com/FUTUREEEEEE/CogniBench) framework, it specifically addresses the challenge of evaluating inference-based statements beyond simple fact regurgitation.
 ## Key Features ✨
 1. **Dual Detection Capability**
@@ -55,7 +54,9 @@ model = AutoModelForCausalLM.from_pretrained(model_id)
 def detect_hallucinations(context, response):
     inputs = tokenizer(
-        f"CONTEXT: {context}\nRESPONSE: {response}\nHALLUCINATIONS:",
         return_tensors="pt"
     )
     outputs = model.generate(**inputs, max_new_tokens=100)

 ---
+base_model:
+- meta-llama/Meta-Llama-3-8B
+datasets:
+- future7/CogniBench
+- future7/CogniBench-L
+language:
+- en
 library_name: transformers
 pipeline_tag: text-generation
 tags:
 - RAG evaluation
 - cognitive statements
 - factual consistency
 ---
 # CogniDet: Cognitive Faithfulness Detector for LLMs
+**CogniDet** is a state-of-the-art model for detecting **both factual and cognitive hallucinations** in Large Language Model (LLM) outputs. Developed as part of the [CogniBench](https://github.com/FUTUREEEEEE/CogniBench) framework, it specifically addresses the challenge of evaluating inference-based statements beyond simple fact regurgitation. The model is presented in the paper [CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models](https://huggingface.co/papers/2505.20767).
 ## Key Features ✨
 1. **Dual Detection Capability**
 def detect_hallucinations(context, response):
     inputs = tokenizer(
+        f"CONTEXT: {context}
+RESPONSE: {response}
+HALLUCINATIONS:",
         return_tensors="pt"
     )
     outputs = model.generate(**inputs, max_new_tokens=100)