Instructions to use Feudor2/hallucination_bin_detector_v5.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Feudor2/hallucination_bin_detector_v5.0 with Transformers:

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

pipe = pipeline("text-generation", model="Feudor2/hallucination_bin_detector_v5.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Feudor2/hallucination_bin_detector_v5.0")
model = AutoModelForCausalLM.from_pretrained("Feudor2/hallucination_bin_detector_v5.0")
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

vLLM

How to use Feudor2/hallucination_bin_detector_v5.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Feudor2/hallucination_bin_detector_v5.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Feudor2/hallucination_bin_detector_v5.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Feudor2/hallucination_bin_detector_v5.0

SGLang

How to use Feudor2/hallucination_bin_detector_v5.0 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 "Feudor2/hallucination_bin_detector_v5.0" \
    --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": "Feudor2/hallucination_bin_detector_v5.0",
		"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 "Feudor2/hallucination_bin_detector_v5.0" \
        --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": "Feudor2/hallucination_bin_detector_v5.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Feudor2/hallucination_bin_detector_v5.0 with Docker Model Runner:
```
docker model run hf.co/Feudor2/hallucination_bin_detector_v5.0
```

hallucination_bin_detector_v5.0

This model is a fine-tuned version of yandex/YandexGPT-5-Lite-8B-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3185

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 1337
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.4949	0.1761	16	0.3654
0.3472	0.3521	32	1.0689
0.3339	0.5282	48	0.3398
0.3304	0.7043	64	0.3233
0.3537	0.8803	80	0.3452
4.267	1.0564	96	0.3771
0.5422	1.2325	112	0.4663
0.3957	1.4085	128	0.3663
0.3469	1.5846	144	0.3320
0.3205	1.7607	160	0.3308
0.4317	1.9367	176	0.3806
0.3469	2.1128	192	0.3385
0.3543	2.2889	208	0.3286
0.3339	2.4649	224	0.3218
0.3643	2.6410	240	0.3360
0.3198	2.8171	256	0.3317
0.3504	2.9931	272	0.3321
0.3195	3.1692	288	0.3276
0.3496	3.3453	304	0.3215
0.3176	3.5213	320	0.3228
0.3175	3.6974	336	0.3226
0.3482	3.8735	352	0.3213
0.3343	4.0495	368	0.3193
0.3262	4.2256	384	0.3205
0.3534	4.4017	400	0.3195
0.3088	4.5777	416	0.3176
0.341	4.7538	432	0.3191
0.3503	4.9298	448	0.3185

Framework versions

Transformers 4.45.2
Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
Datasets 4.4.1
Tokenizers 0.20.3

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Feudor2/hallucination_bin_detector_v5.0

Base model

yandex/YandexGPT-5-Lite-8B-pretrain

Finetuned

yandex/YandexGPT-5-Lite-8B-instruct

Finetuned

(11)

this model