Instructions to use rbelanec/train_math_qa_42_1760637607 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_math_qa_42_1760637607 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_42_1760637607")

Transformers

How to use rbelanec/train_math_qa_42_1760637607 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_math_qa_42_1760637607")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_math_qa_42_1760637607", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_math_qa_42_1760637607 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_42_1760637607"
# 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_42_1760637607",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_math_qa_42_1760637607

SGLang

How to use rbelanec/train_math_qa_42_1760637607 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_42_1760637607" \
    --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_42_1760637607",
		"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_42_1760637607" \
        --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_42_1760637607",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_math_qa_42_1760637607 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_math_qa_42_1760637607
```

train_math_qa_42_1760637607

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: 0.6375
Num Input Tokens Seen: 77902976

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: 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
0.5315	1.0	6714	0.6721	3894552
0.6586	2.0	13428	0.6469	7790784
0.5869	3.0	20142	0.6375	11684296
0.5139	4.0	26856	0.7031	15578848
0.3445	5.0	33570	0.8775	19476576
0.1427	6.0	40284	1.0436	23368392
0.1597	7.0	46998	1.3234	27263880
0.2681	8.0	53712	1.4101	31154960
0.0754	9.0	60426	1.4897	35053760
0.4251	10.0	67140	1.6455	38947216
0.0184	11.0	73854	1.8252	42844400
0.0371	12.0	80568	1.8437	46741816
0.0	13.0	87282	2.0766	50638456
0.1223	14.0	93996	2.2302	54533112
0.0	15.0	100710	2.4064	58429624
0.0084	16.0	107424	3.1546	62323952
0.0	17.0	114138	3.3436	66220752
0.0	18.0	120852	3.6660	70113640
0.0	19.0	127566	3.8155	74009160
0.0	20.0	134280	3.8375	77902976

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_42_1760637607

Base model

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

Adapter

(2403)

this model