Instructions to use rbelanec/train_qqp_42_1779354536 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_qqp_42_1779354536 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_qqp_42_1779354536")
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_1779354536")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_qqp_42_1779354536")
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_1779354536 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_1779354536"
# 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_1779354536",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_qqp_42_1779354536

SGLang

How to use rbelanec/train_qqp_42_1779354536 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_1779354536" \
    --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_1779354536",
		"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_1779354536" \
        --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_1779354536",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_qqp_42_1779354536 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_qqp_42_1779354536
```

train_qqp_42_1779354536

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: 0.0971
Num Input Tokens Seen: 27589664

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
0.2949	0.0500	2047	0.1455	1392320
0.1591	0.1000	4094	0.1452	2766976
0.194	0.1500	6141	0.1621	4153792
0.0573	0.2000	8188	0.1290	5528512
0.2024	0.2500	10235	0.1197	6911360
0.0685	0.3001	12282	0.1198	8281152
0.1171	0.3501	14329	0.1189	9655616
0.0261	0.4001	16376	0.1129	11025600
0.0561	0.4501	18423	0.1114	12395840
0.1968	0.5001	20470	0.1074	13782144
0.0355	0.5501	22517	0.1015	15155072
0.0953	0.6001	24564	0.0971	16541888
0.0205	0.6501	26611	0.1038	17928960
0.0953	0.7001	28658	0.1138	19303296
0.1044	0.7501	30705	0.1024	20683008
0.0655	0.8001	32752	0.0997	22064384
0.0883	0.8501	34799	0.1071	23443136
0.0633	0.9002	36846	0.1085	24829568
0.045	0.9502	38893	0.1052	26221120

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 248

Safetensors

Model size

1B params

Tensor type

F32

Model tree for rbelanec/train_qqp_42_1779354536

Base model

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

Finetuned

(1747)

this model