Instructions to use rbelanec/train_math_qa_456_1760637840 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_math_qa_456_1760637840 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_math_qa_456_1760637840")

Transformers

How to use rbelanec/train_math_qa_456_1760637840 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_math_qa_456_1760637840")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_math_qa_456_1760637840", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_math_qa_456_1760637840 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_math_qa_456_1760637840"
# 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_math_qa_456_1760637840",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_math_qa_456_1760637840

SGLang

How to use rbelanec/train_math_qa_456_1760637840 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_math_qa_456_1760637840" \
    --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_math_qa_456_1760637840",
		"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_math_qa_456_1760637840" \
        --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_math_qa_456_1760637840",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_math_qa_456_1760637840 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_math_qa_456_1760637840
```

train_math_qa_456_1760637840

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

Loss: 0.6754
Num Input Tokens Seen: 77891968

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
0.7605	1.0	6714	0.7289	3900904
0.7221	2.0	13428	0.7029	7795688
0.6497	3.0	20142	0.6900	11690736
0.7142	4.0	26856	0.6831	15583992
0.7064	5.0	33570	0.6796	19477680
0.6105	6.0	40284	0.6763	23372072
0.5207	7.0	46998	0.6786	27267240
0.5292	8.0	53712	0.6772	31161216
0.6516	9.0	60426	0.6754	35058040
0.4422	10.0	67140	0.6811	38955336
0.5215	11.0	73854	0.6783	42849552
0.5573	12.0	80568	0.6801	46744544
0.53	13.0	87282	0.6764	50638504
0.5698	14.0	93996	0.6842	54532704
0.6609	15.0	100710	0.6799	58424776
0.509	16.0	107424	0.6812	62319120
0.7441	17.0	114138	0.6821	66209648
0.414	18.0	120852	0.6827	70104328
0.6172	19.0	127566	0.6819	73997656
0.3372	20.0	134280	0.6830	77891968

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_math_qa_456_1760637840

Base model

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

Adapter

(2402)

this model