Instructions to use rbelanec/train_siqa_42_1760637603 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_siqa_42_1760637603 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_1760637603")

Transformers

How to use rbelanec/train_siqa_42_1760637603 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_siqa_42_1760637603")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_siqa_42_1760637603", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_siqa_42_1760637603 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_1760637603"
# 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_1760637603",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_siqa_42_1760637603

SGLang

How to use rbelanec/train_siqa_42_1760637603 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_1760637603" \
    --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_1760637603",
		"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_1760637603" \
        --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_1760637603",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_siqa_42_1760637603 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_siqa_42_1760637603
```

train_siqa_42_1760637603

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: 0.1864
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: 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
0.2368	1.0	7518	0.2649	3016248
0.2489	2.0	15036	0.2272	6032368
0.2042	3.0	22554	0.2101	9049000
0.2619	4.0	30072	0.1998	12063104
0.1616	5.0	37590	0.1930	15078392
0.1992	6.0	45108	0.1900	18094200
0.2646	7.0	52626	0.1882	21109936
0.1471	8.0	60144	0.1864	24124456
0.1564	9.0	67662	0.1867	27139488
0.1005	10.0	75180	0.1881	30155824
0.0864	11.0	82698	0.1869	33169800
0.2135	12.0	90216	0.1865	36184296
0.1404	13.0	97734	0.1875	39199224
0.1005	14.0	105252	0.1869	42213984
0.1063	15.0	112770	0.1882	45227616
0.0492	16.0	120288	0.1899	48242336
0.1124	17.0	127806	0.1893	51258152
0.1073	18.0	135324	0.1893	54272896
0.2107	19.0	142842	0.1892	57288368
0.0852	20.0	150360	0.1891	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_1760637603

Base model

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

Adapter

(2405)

this model