Instructions to use rbelanec/train_stsb_456_1760637814 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_stsb_456_1760637814 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_stsb_456_1760637814")

Transformers

How to use rbelanec/train_stsb_456_1760637814 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_stsb_456_1760637814")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_stsb_456_1760637814", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_stsb_456_1760637814 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_stsb_456_1760637814"
# 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_stsb_456_1760637814",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_stsb_456_1760637814

SGLang

How to use rbelanec/train_stsb_456_1760637814 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_stsb_456_1760637814" \
    --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_stsb_456_1760637814",
		"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_stsb_456_1760637814" \
        --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_stsb_456_1760637814",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_stsb_456_1760637814 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_stsb_456_1760637814
```

train_stsb_456_1760637814

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

Loss: 0.4446
Num Input Tokens Seen: 8714656

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 456
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
1.0243	1.0	1294	1.0522	435104
0.5072	2.0	2588	0.6118	870112
0.4585	3.0	3882	0.5377	1305024
0.4735	4.0	5176	0.5074	1742048
0.4916	5.0	6470	0.4902	2176672
0.4197	6.0	7764	0.4768	2613648
0.5125	7.0	9058	0.4705	3049776
0.5041	8.0	10352	0.4627	3486928
0.3721	9.0	11646	0.4601	3924192
0.3501	10.0	12940	0.4545	4360736
0.603	11.0	14234	0.4522	4793520
0.3599	12.0	15528	0.4499	5230528
0.5075	13.0	16822	0.4493	5664848
0.561	14.0	18116	0.4477	6100288
0.3745	15.0	19410	0.4466	6534240
0.5419	16.0	20704	0.4456	6969936
0.4025	17.0	21998	0.4446	7405056
0.3401	18.0	23292	0.4447	7842624
0.4637	19.0	24586	0.4462	8279952
0.5089	20.0	25880	0.4453	8714656

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_stsb_456_1760637814

Base model

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

Adapter

(2402)

this model