Instructions to use denisdrobs/business-news-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use denisdrobs/business-news-generator with Transformers:

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

pipe = pipeline("text-generation", model="denisdrobs/business-news-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("denisdrobs/business-news-generator")
model = AutoModelForCausalLM.from_pretrained("denisdrobs/business-news-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use denisdrobs/business-news-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/denisdrobs/business-news-generator

SGLang

How to use denisdrobs/business-news-generator 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 "denisdrobs/business-news-generator" \
    --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": "denisdrobs/business-news-generator",
		"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 "denisdrobs/business-news-generator" \
        --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": "denisdrobs/business-news-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use denisdrobs/business-news-generator with Docker Model Runner:
```
docker model run hf.co/denisdrobs/business-news-generator
```

business-news-generator

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.6352

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: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.995	0.0667	250	2.9110
2.7841	0.1333	500	2.8087
2.6712	0.2	750	2.7404
2.6066	0.2667	1000	2.6879
2.6106	0.3333	1250	2.6502
2.4939	0.4	1500	2.6098
2.4882	0.4667	1750	2.5833
2.4643	0.5333	2000	2.5502
2.5015	0.6	2250	2.5292
2.4297	0.6667	2500	2.5005
2.4226	0.7333	2750	2.4799
2.3655	0.8	3000	2.4628
2.3618	0.8667	3250	2.4479
2.3564	0.9333	3500	2.4245
2.3139	1.0	3750	2.4075
1.9111	1.0667	4000	2.4290
1.8905	1.1333	4250	2.4294
1.9087	1.2	4500	2.4133
1.8783	1.2667	4750	2.4113
1.9007	1.3333	5000	2.3973
1.8779	1.4	5250	2.3974
1.8838	1.4667	5500	2.3762
1.8876	1.5333	5750	2.3705
1.8823	1.6	6000	2.3576
1.8441	1.6667	6250	2.3606
1.9025	1.7333	6500	2.3369
1.8762	1.8	6750	2.3354
1.8519	1.8667	7000	2.3206
1.836	1.9333	7250	2.3161
1.8376	2.0	7500	2.3036
1.4173	2.0667	7750	2.4042
1.4096	2.1333	8000	2.4170
1.397	2.2	8250	2.4074
1.4091	2.2667	8500	2.4025
1.3757	2.3333	8750	2.3960
1.4316	2.4	9000	2.3916
1.4122	2.4667	9250	2.3924
1.4233	2.5333	9500	2.3840
1.4013	2.6	9750	2.3826
1.4185	2.6667	10000	2.3819
1.4194	2.7333	10250	2.3753
1.3845	2.8	10500	2.3715
1.4001	2.8667	10750	2.3718
1.3974	2.9333	11000	2.3670
1.3913	3.0	11250	2.3537
1.0379	3.0667	11500	2.4938
1.0278	3.1333	11750	2.5113
1.0213	3.2	12000	2.5104
1.0384	3.2667	12250	2.5112
1.0286	3.3333	12500	2.5135
1.0372	3.4	12750	2.5206
1.0279	3.4667	13000	2.5075
1.035	3.5333	13250	2.5152
1.0314	3.6	13500	2.5142
1.0288	3.6667	13750	2.5158
1.0307	3.7333	14000	2.5070
1.0498	3.8	14250	2.5013
1.0358	3.8667	14500	2.5039
1.0087	3.9333	14750	2.5064
1.0201	4.0	15000	2.5032
0.8131	4.0667	15250	2.6065
0.8109	4.1333	15500	2.6206
0.7992	4.2	15750	2.6228
0.8171	4.2667	16000	2.6280
0.8101	4.3333	16250	2.6320
0.8125	4.4	16500	2.6342
0.8281	4.4667	16750	2.6324
0.8258	4.5333	17000	2.6351
0.8181	4.6	17250	2.6346
0.8096	4.6667	17500	2.6347
0.8222	4.7333	17750	2.6350
0.8283	4.8	18000	2.6351
0.8115	4.8667	18250	2.6355
0.8302	4.9333	18500	2.6352
0.8163	5.0	18750	2.6352

Framework versions

Transformers 4.56.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0

Downloads last month: 5

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for denisdrobs/business-news-generator

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(938)

this model