Instructions to use rbelanec/train_qqp_42_1779207273 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_qqp_42_1779207273 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_qqp_42_1779207273")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_qqp_42_1779207273")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_qqp_42_1779207273")
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 rbelanec/train_qqp_42_1779207273 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_qqp_42_1779207273"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_qqp_42_1779207273",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_qqp_42_1779207273

SGLang

How to use rbelanec/train_qqp_42_1779207273 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 "rbelanec/train_qqp_42_1779207273" \
    --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": "rbelanec/train_qqp_42_1779207273",
		"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 "rbelanec/train_qqp_42_1779207273" \
        --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": "rbelanec/train_qqp_42_1779207273",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_qqp_42_1779207273 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_qqp_42_1779207273
```

train_qqp_42_1779207273

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the qqp dataset. It achieves the following results on the evaluation set:

Loss: 0.1128
Num Input Tokens Seen: 137941664

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: 2e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.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: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.1388	0.2500	10234	0.1504	6910656
0.1021	0.5000	20468	0.1128	13780928
0.0459	0.7501	30702	0.1215	20680640
0.1214	1.0001	40936	0.1224	27591776
0.1395	1.2501	51170	0.1528	34492320
0.0425	1.5001	61404	0.1524	41393504
0.1097	1.7501	71638	0.1231	48287456
0.0019	2.0001	81872	0.1237	55178600
0.0001	2.2502	92106	0.2041	62093992
0.0236	2.5002	102340	0.1835	68988456
0.0008	2.7502	112574	0.2039	75874280
0.0003	3.0002	122808	0.1936	82772304
0.0	3.2502	133042	0.2610	89675984
0.0332	3.5003	143276	0.2494	96560720
0.0	3.7503	153510	0.2414	103465808
0.0	4.0003	163744	0.2473	110357352
0.0	4.2503	173978	0.3375	117230952
0.0	4.5003	184212	0.3128	124100264
0.0727	4.7503	194446	0.3178	131030440

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 308

Safetensors

Model size

1B params

Tensor type

F32

Model tree for rbelanec/train_qqp_42_1779207273

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1747)

this model