Instructions to use rbelanec/train_qnli_42_1779286680 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_qnli_42_1779286680 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_qnli_42_1779286680")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_qnli_42_1779286680")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_qnli_42_1779286680")
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_qnli_42_1779286680 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_qnli_42_1779286680"
# 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_qnli_42_1779286680",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_qnli_42_1779286680

SGLang

How to use rbelanec/train_qnli_42_1779286680 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_qnli_42_1779286680" \
    --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_qnli_42_1779286680",
		"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_qnli_42_1779286680" \
        --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_qnli_42_1779286680",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_qnli_42_1779286680 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_qnli_42_1779286680
```

train_qnli_42_1779286680

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

Loss: 0.0523
Num Input Tokens Seen: 11312256

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.0929	0.0501	590	0.0807	571072
0.1054	0.1001	1180	0.0708	1136384
0.1201	0.1502	1770	0.0836	1703808
0.1436	0.2003	2360	0.0888	2266496
0.0749	0.2503	2950	0.0761	2827328
0.0141	0.3004	3540	0.0862	3399808
0.0051	0.3505	4130	0.0710	3963584
0.0782	0.4005	4720	0.0551	4530304
0.05	0.4506	5310	0.0634	5095424
0.0293	0.5007	5900	0.0550	5660352
0.0534	0.5507	6490	0.0558	6232896
0.0467	0.6008	7080	0.0598	6801984
0.0404	0.6509	7670	0.0556	7363968
0.0633	0.7010	8260	0.0546	7924800
0.0632	0.7510	8850	0.0540	8494720
0.1023	0.8011	9440	0.0547	9066048
0.0665	0.8512	10030	0.0526	9634624
0.0855	0.9012	10620	0.0523	10199424
0.004	0.9513	11210	0.0523	10764096

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 234

Safetensors

Model size

1B params

Tensor type

F32

BF16

Model tree for rbelanec/train_qnli_42_1779286680

Base model

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

Finetuned

(1748)

this model