Instructions to use rbelanec/train_sst2_42_1760637620 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_sst2_42_1760637620 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbelanec/train_sst2_42_1760637620")

Transformers

How to use rbelanec/train_sst2_42_1760637620 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_sst2_42_1760637620")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_sst2_42_1760637620", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_sst2_42_1760637620 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_1760637620"
# 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_1760637620",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_sst2_42_1760637620

SGLang

How to use rbelanec/train_sst2_42_1760637620 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_1760637620" \
    --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_1760637620",
		"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_1760637620" \
        --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_1760637620",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_sst2_42_1760637620 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_sst2_42_1760637620
```

train_sst2_42_1760637620

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the sst2 dataset. It achieves the following results on the evaluation set:

Loss: 0.0880
Num Input Tokens Seen: 67768656

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: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
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: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.1921	1.0	15154	0.0587	3383904
0.0499	2.0	30308	0.0632	6774480
0.0157	3.0	45462	0.0565	10163152
0.1249	4.0	60616	0.0541	13552544
0.1162	5.0	75770	0.0562	16941120
0.1054	6.0	90924	0.0526	20331520
0.0054	7.0	106078	0.0538	23721840
0.0269	8.0	121232	0.0534	27111168
0.155	9.0	136386	0.0540	30498912
0.1169	10.0	151540	0.0564	33886240
0.0167	11.0	166694	0.0594	37277536
0.0091	12.0	181848	0.0614	40664576
0.0062	13.0	197002	0.0653	44053792
0.0236	14.0	212156	0.0692	47441984
0.0485	15.0	227310	0.0734	50830480
0.0047	16.0	242464	0.0758	54215696
0.0019	17.0	257618	0.0807	57603296
0.0027	18.0	272772	0.0857	60987568
0.0018	19.0	287926	0.0880	64378192
0.001	20.0	303080	0.0879	67768656

Framework versions

PEFT 0.17.1
Transformers 4.51.3
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for rbelanec/train_sst2_42_1760637620

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Adapter

(2402)

this model