Instructions to use rbelanec/train_sst2_42_1779354538 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_sst2_42_1779354538 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_sst2_42_1779354538")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_sst2_42_1779354538")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_sst2_42_1779354538")
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 Settings

vLLM

How to use rbelanec/train_sst2_42_1779354538 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_sst2_42_1779354538"
# 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_sst2_42_1779354538",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_sst2_42_1779354538

SGLang

How to use rbelanec/train_sst2_42_1779354538 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_sst2_42_1779354538" \
    --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_sst2_42_1779354538",
		"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_sst2_42_1779354538" \
        --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_sst2_42_1779354538",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_sst2_42_1779354538 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_sst2_42_1779354538
```

train_sst2_42_1779354538

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the sst2 dataset. It achieves the following results on the evaluation set:

Loss: 0.0936
Num Input Tokens Seen: 3725120

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
0.0578	0.0500	379	0.1688	187072
0.1097	0.1000	758	0.1367	373504
0.0564	0.1501	1137	0.1656	557824
0.1883	0.2001	1516	0.1097	743424
0.2857	0.2501	1895	0.1319	930944
0.1387	0.3001	2274	0.1241	1116800
0.0494	0.3501	2653	0.1384	1303872
0.1412	0.4002	3032	0.1309	1490688
0.0509	0.4502	3411	0.1158	1678208
0.179	0.5002	3790	0.1276	1864128
0.1555	0.5502	4169	0.0994	2047552
0.1894	0.6002	4548	0.1099	2232448
0.1297	0.6503	4927	0.0997	2420096
0.1829	0.7003	5306	0.0936	2605504
0.0314	0.7503	5685	0.1006	2790656
0.1396	0.8003	6064	0.0963	2979456
0.171	0.8503	6443	0.1007	3167488
0.0013	0.9004	6822	0.0976	3355520
0.0683	0.9504	7201	0.0981	3541632

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 190

Safetensors

Model size

1B params

Tensor type

F32

Model tree for rbelanec/train_sst2_42_1779354538

Base model

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

Finetuned

(1751)

this model