Instructions to use linnotlinn/commonpile-shuffled-1234-pythia-70m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use linnotlinn/commonpile-shuffled-1234-pythia-70m with Transformers:

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

pipe = pipeline("text-generation", model="linnotlinn/commonpile-shuffled-1234-pythia-70m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("linnotlinn/commonpile-shuffled-1234-pythia-70m")
model = AutoModelForCausalLM.from_pretrained("linnotlinn/commonpile-shuffled-1234-pythia-70m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use linnotlinn/commonpile-shuffled-1234-pythia-70m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "linnotlinn/commonpile-shuffled-1234-pythia-70m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linnotlinn/commonpile-shuffled-1234-pythia-70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/linnotlinn/commonpile-shuffled-1234-pythia-70m

SGLang

How to use linnotlinn/commonpile-shuffled-1234-pythia-70m 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 "linnotlinn/commonpile-shuffled-1234-pythia-70m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linnotlinn/commonpile-shuffled-1234-pythia-70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "linnotlinn/commonpile-shuffled-1234-pythia-70m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linnotlinn/commonpile-shuffled-1234-pythia-70m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use linnotlinn/commonpile-shuffled-1234-pythia-70m with Docker Model Runner:
```
docker model run hf.co/linnotlinn/commonpile-shuffled-1234-pythia-70m
```

commonpile-shuffled-1234-pythia-70m

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.0994

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: 0.0002
train_batch_size: 32
eval_batch_size: 32
seed: 1234
gradient_accumulation_steps: 16
total_train_batch_size: 512
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_steps: 20
num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss
6.1687	0.4993	140	6.1345
5.5313	0.9987	280	5.5008
5.1863	1.4958	420	5.1829
4.9825	1.9951	560	4.9861
4.8390	2.4922	700	4.8477
4.7299	2.9915	840	4.7381
4.6319	3.4886	980	4.6530
4.5634	3.9880	1120	4.5823
4.4850	4.4851	1260	4.5221
4.4487	4.9844	1400	4.4754
4.3898	5.4815	1540	4.4311
4.3604	5.9808	1680	4.3933
4.3094	6.4779	1820	4.3620
4.2870	6.9773	1960	4.3312
4.2419	7.4744	2100	4.3109
4.2343	7.9737	2240	4.2851
4.1907	8.4708	2380	4.2659
4.1809	8.9701	2520	4.2455
4.1510	9.4672	2660	4.2318
4.1364	9.9666	2800	4.2138
4.1035	10.4637	2940	4.2047
4.1062	10.9630	3080	4.1906
4.0760	11.4601	3220	4.1806
4.0761	11.9594	3360	4.1693
4.0591	12.4565	3500	4.1629
4.0580	12.9559	3640	4.1522
4.0254	13.4530	3780	4.1471
4.0247	13.9523	3920	4.1387
3.9980	14.4494	4060	4.1348
4.0105	14.9487	4200	4.1279
3.9955	15.4458	4340	4.1248
3.9964	15.9452	4480	4.1193
3.9827	16.4423	4620	4.1167
3.9823	16.9416	4760	4.1129
3.9640	17.4387	4900	4.1108
3.9635	17.9380	5040	4.1069
3.9627	18.4351	5180	4.1057
3.9634	18.9345	5320	4.1030
3.9607	19.4316	5460	4.1019
3.9561	19.9309	5600	4.0994
3.9550	20.0	5620	4.0996

Framework versions

Transformers 5.13.0
Pytorch 2.11.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2

Downloads last month: 461

Safetensors

Model size

70.4M params

Tensor type

F32