Instructions to use lightblue/reranker_0.5_cont_filt_7max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lightblue/reranker_0.5_cont_filt_7max with Transformers:

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

pipe = pipeline("text-generation", model="lightblue/reranker_0.5_cont_filt_7max")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lightblue/reranker_0.5_cont_filt_7max")
model = AutoModelForCausalLM.from_pretrained("lightblue/reranker_0.5_cont_filt_7max")
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

vLLM

How to use lightblue/reranker_0.5_cont_filt_7max with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lightblue/reranker_0.5_cont_filt_7max"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightblue/reranker_0.5_cont_filt_7max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lightblue/reranker_0.5_cont_filt_7max

SGLang

How to use lightblue/reranker_0.5_cont_filt_7max 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 "lightblue/reranker_0.5_cont_filt_7max" \
    --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": "lightblue/reranker_0.5_cont_filt_7max",
		"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 "lightblue/reranker_0.5_cont_filt_7max" \
        --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": "lightblue/reranker_0.5_cont_filt_7max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lightblue/reranker_0.5_cont_filt_7max with Docker Model Runner:
```
docker model run hf.co/lightblue/reranker_0.5_cont_filt_7max
```

reranker_continuous_filt_max7_train

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_continuous_filt_max7_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3869

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.403	0.1000	1977	0.4783
0.5192	0.2000	3954	0.4524
0.3639	0.3000	5931	0.4370
0.4343	0.4000	7908	0.4286
0.3929	0.5000	9885	0.4163
0.4455	0.6000	11862	0.4040
0.3775	0.7000	13839	0.3947
0.3629	0.8000	15816	0.3898
0.5186	0.9000	17793	0.3872

Framework versions

Transformers 4.46.1
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

Downloads last month: 4

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for lightblue/reranker_0.5_cont_filt_7max

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(764)

this model