Instructions to use rbelanec/train_siqa_42_1760637600 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_siqa_42_1760637600 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_siqa_42_1760637600")

Transformers

How to use rbelanec/train_siqa_42_1760637600 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_siqa_42_1760637600")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_siqa_42_1760637600", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_siqa_42_1760637600 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_siqa_42_1760637600"
# 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_siqa_42_1760637600",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_siqa_42_1760637600

SGLang

How to use rbelanec/train_siqa_42_1760637600 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_siqa_42_1760637600" \
    --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_siqa_42_1760637600",
		"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_siqa_42_1760637600" \
        --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_siqa_42_1760637600",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_siqa_42_1760637600 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_siqa_42_1760637600
```

train_siqa_42_1760637600

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

Loss: 0.3242
Num Input Tokens Seen: 60302568

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: 0.001
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
0.5513	1.0	7518	0.5516	3016248
0.3912	2.0	15036	0.4717	6032368
0.2175	3.0	22554	0.1947	9049000
0.249	4.0	30072	0.1910	12063104
0.1141	5.0	37590	0.1794	15078392
0.1228	6.0	45108	0.1795	18094200
0.2971	7.0	52626	0.1823	21109936
0.1088	8.0	60144	0.1789	24124456
0.1078	9.0	67662	0.1822	27139488
0.092	10.0	75180	0.1864	30155824
0.0864	11.0	82698	0.1988	33169800
0.1477	12.0	90216	0.2067	36184296
0.0384	13.0	97734	0.2242	39199224
0.0201	14.0	105252	0.2517	42213984
0.0229	15.0	112770	0.2795	45227616
0.0055	16.0	120288	0.3139	48242336
0.0268	17.0	127806	0.3421	51258152
0.0525	18.0	135324	0.3645	54272896
0.0094	19.0	142842	0.3786	57288368
0.0056	20.0	150360	0.3844	60302568

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_siqa_42_1760637600

Base model

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

Adapter

(2404)

this model