Instructions to use fpadovani/de_child_clm_42_new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fpadovani/de_child_clm_42_new with Transformers:

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

pipe = pipeline("text-generation", model="fpadovani/de_child_clm_42_new")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fpadovani/de_child_clm_42_new")
model = AutoModelForCausalLM.from_pretrained("fpadovani/de_child_clm_42_new", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fpadovani/de_child_clm_42_new with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fpadovani/de_child_clm_42_new"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fpadovani/de_child_clm_42_new",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fpadovani/de_child_clm_42_new

SGLang

How to use fpadovani/de_child_clm_42_new 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 "fpadovani/de_child_clm_42_new" \
    --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": "fpadovani/de_child_clm_42_new",
		"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 "fpadovani/de_child_clm_42_new" \
        --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": "fpadovani/de_child_clm_42_new",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fpadovani/de_child_clm_42_new with Docker Model Runner:
```
docker model run hf.co/fpadovani/de_child_clm_42_new
```

de_childes_42

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

Loss: 4.1897

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: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 40000
training_steps: 100000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.5021	2000	7.0336
6.9417	3.0041	4000	5.8112
6.9417	4.5062	6000	5.4586
5.2077	6.0083	8000	5.1717
5.2077	7.5103	10000	4.9583
4.7315	9.0124	12000	4.8002
4.7315	10.5145	14000	4.6706
4.4253	12.0165	16000	4.5552
4.4253	13.5186	18000	4.4522
4.1962	15.0207	20000	4.3739
4.1962	16.5227	22000	4.2925
4.0105	18.0248	24000	4.2277
4.0105	19.5268	26000	4.1706
3.857	21.0289	28000	4.1245
3.857	22.5310	30000	4.0846
3.7298	24.0330	32000	4.0589
3.7298	25.5351	34000	4.0266
3.6218	27.0372	36000	4.0028
3.6218	28.5392	38000	3.9863
3.5278	30.0413	40000	3.9732
3.5278	31.5434	42000	3.9720
3.4351	33.0454	44000	3.9599
3.4351	34.5475	46000	3.9566
3.3444	36.0496	48000	3.9572
3.3444	37.5516	50000	3.9680
3.2651	39.0537	52000	3.9788
3.2651	40.5558	54000	3.9815
3.1966	42.0578	56000	3.9928
3.1966	43.5599	58000	4.0061
3.1344	45.0620	60000	4.0126
3.1344	46.5640	62000	4.0198
3.0785	48.0661	64000	4.0377
3.0785	49.5682	66000	4.0502
3.0287	51.0702	68000	4.0644
3.0287	52.5723	70000	4.0714
2.9837	54.0744	72000	4.0852
2.9837	55.5764	74000	4.0964
2.9422	57.0785	76000	4.1148
2.9422	58.5805	78000	4.1221
2.9052	60.0826	80000	4.1276
2.9052	61.5847	82000	4.1346
2.8708	63.0867	84000	4.1505
2.8708	64.5888	86000	4.1574
2.839	66.0909	88000	4.1675
2.839	67.5929	90000	4.1727
2.8117	69.0950	92000	4.1767
2.8117	70.5971	94000	4.1823
2.7886	72.0991	96000	4.1867
2.7886	73.6012	98000	4.1872
2.768	75.1033	100000	4.1897

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu124
Datasets 3.0.1
Tokenizers 0.20.1

Downloads last month: 11

Safetensors

Model size

12.7M params

Tensor type

F32