Instructions to use rbelanec/train_rte_123_1760637670 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_rte_123_1760637670 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_rte_123_1760637670")

Transformers

How to use rbelanec/train_rte_123_1760637670 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_rte_123_1760637670")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_rte_123_1760637670", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rbelanec/train_rte_123_1760637670 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_rte_123_1760637670"
# 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_rte_123_1760637670",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_rte_123_1760637670

SGLang

How to use rbelanec/train_rte_123_1760637670 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_rte_123_1760637670" \
    --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_rte_123_1760637670",
		"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_rte_123_1760637670" \
        --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_rte_123_1760637670",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_rte_123_1760637670 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_rte_123_1760637670
```

train_rte_123_1760637670

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

Loss: 0.1551
Num Input Tokens Seen: 6958720

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: 0.03
train_batch_size: 4
eval_batch_size: 4
seed: 123
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
0.1666	1.0	561	0.1581	348144
0.1686	2.0	1122	0.1622	697760
0.1574	3.0	1683	0.1598	1046680
0.1577	4.0	2244	0.1571	1394776
0.1576	5.0	2805	0.1572	1743216
0.1527	6.0	3366	0.1552	2088384
0.1557	7.0	3927	0.1551	2437304
0.1652	8.0	4488	0.1570	2785744
0.145	9.0	5049	0.1554	3132040
0.1481	10.0	5610	0.1571	3481336
0.1599	11.0	6171	0.1582	3829824
0.1525	12.0	6732	0.1583	4180088
0.1627	13.0	7293	0.1570	4527216
0.1409	14.0	7854	0.1570	4875496
0.1478	15.0	8415	0.1590	5222072
0.1539	16.0	8976	0.1611	5571288
0.1383	17.0	9537	0.1638	5918280
0.1432	18.0	10098	0.1649	6268760
0.139	19.0	10659	0.1655	6614344
0.1455	20.0	11220	0.1649	6958720

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_rte_123_1760637670

Base model

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

Adapter

(2405)

this model