Instructions to use rbelanec/train_openbookqa_456_1760637802 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_openbookqa_456_1760637802 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_openbookqa_456_1760637802")

Transformers

How to use rbelanec/train_openbookqa_456_1760637802 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_openbookqa_456_1760637802")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_openbookqa_456_1760637802", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_openbookqa_456_1760637802 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_openbookqa_456_1760637802"
# 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_openbookqa_456_1760637802",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_openbookqa_456_1760637802

SGLang

How to use rbelanec/train_openbookqa_456_1760637802 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_openbookqa_456_1760637802" \
    --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_openbookqa_456_1760637802",
		"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_openbookqa_456_1760637802" \
        --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_openbookqa_456_1760637802",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_openbookqa_456_1760637802 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_openbookqa_456_1760637802
```

train_openbookqa_456_1760637802

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

Loss: 0.2063
Num Input Tokens Seen: 8491296

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
0.4303	1.0	1116	0.3384	424016
0.2794	2.0	2232	0.2649	848912
0.4794	3.0	3348	0.2403	1273224
0.1947	4.0	4464	0.2280	1698344
0.1539	5.0	5580	0.2193	2122168
0.078	6.0	6696	0.2148	2547696
0.2228	7.0	7812	0.2116	2971624
0.2844	8.0	8928	0.2094	3395952
0.4213	9.0	10044	0.2064	3821456
0.1053	10.0	11160	0.2075	4245816
0.1091	11.0	12276	0.2063	4670528
0.2387	12.0	13392	0.2072	5093960
0.1534	13.0	14508	0.2066	5519312
0.2197	14.0	15624	0.2076	5944728
0.0937	15.0	16740	0.2087	6369088
0.1775	16.0	17856	0.2071	6792536
0.0811	17.0	18972	0.2086	7217384
0.1764	18.0	20088	0.2087	7642368
0.1422	19.0	21204	0.2091	8066544
0.0498	20.0	22320	0.2090	8491296

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_openbookqa_456_1760637802

Base model

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

Adapter

(2404)

this model