Instructions to use rbelanec/train_winogrande_789_1760637960 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_winogrande_789_1760637960 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_winogrande_789_1760637960")

Transformers

How to use rbelanec/train_winogrande_789_1760637960 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_winogrande_789_1760637960")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_winogrande_789_1760637960", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rbelanec/train_winogrande_789_1760637960 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_winogrande_789_1760637960"
# 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_winogrande_789_1760637960",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_winogrande_789_1760637960

SGLang

How to use rbelanec/train_winogrande_789_1760637960 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_winogrande_789_1760637960" \
    --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_winogrande_789_1760637960",
		"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_winogrande_789_1760637960" \
        --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_winogrande_789_1760637960",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_winogrande_789_1760637960 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_winogrande_789_1760637960
```

train_winogrande_789_1760637960

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

Loss: 0.0658
Num Input Tokens Seen: 38393344

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: 789
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
0.1644	1.0	9090	0.1500	1919360
0.0934	2.0	18180	0.0913	3838064
0.0491	3.0	27270	0.0791	5755984
0.0401	4.0	36360	0.0730	7675760
0.1736	5.0	45450	0.0694	9596528
0.0123	6.0	54540	0.0680	11515248
0.1022	7.0	63630	0.0669	13435888
0.1314	8.0	72720	0.0658	15356016
0.0363	9.0	81810	0.0722	17274448
0.0051	10.0	90900	0.0720	19194672
0.007	11.0	99990	0.0735	21115984
0.0024	12.0	109080	0.0785	23036144
0.0012	13.0	118170	0.0860	24955120
0.0697	14.0	127260	0.0908	26874400
0.0134	15.0	136350	0.0874	28793728
0.1504	16.0	145440	0.0966	30713760
0.0542	17.0	154530	0.0949	32634016
0.1369	18.0	163620	0.0964	34554208
0.0017	19.0	172710	0.0962	36474880
0.0147	20.0	181800	0.0950	38393344

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_winogrande_789_1760637960

Base model

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

Adapter

(2405)

this model