Instructions to use valer125/business-news-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use valer125/business-news-generator with Transformers:

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

pipe = pipeline("text-generation", model="valer125/business-news-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("valer125/business-news-generator")
model = AutoModelForCausalLM.from_pretrained("valer125/business-news-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use valer125/business-news-generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "valer125/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": "valer125/business-news-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/valer125/business-news-generator

SGLang

How to use valer125/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 "valer125/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": "valer125/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 "valer125/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": "valer125/business-news-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use valer125/business-news-generator with Docker Model Runner:
```
docker model run hf.co/valer125/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: 2.3790

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
3.0819	0.0533	200	2.9697
2.8552	0.1067	400	2.8577
2.6939	0.16	600	2.7927
2.6986	0.2133	800	2.7458
2.6095	0.2667	1000	2.7076
2.6293	0.32	1200	2.6714
2.5621	0.3733	1400	2.6468
2.4916	0.4267	1600	2.6194
2.5108	0.48	1800	2.6019
2.4913	0.5333	2000	2.5772
2.5371	0.5867	2200	2.5577
2.4839	0.64	2400	2.5442
2.4407	0.6933	2600	2.5237
2.4473	0.7467	2800	2.5057
2.3907	0.8	3000	2.4957
2.4092	0.8533	3200	2.4808
2.3844	0.9067	3400	2.4679
2.3855	0.96	3600	2.4564
2.2715	1.0133	3800	2.4553
2.0903	1.0667	4000	2.4500
2.0707	1.12	4200	2.4477
2.0659	1.1733	4400	2.4404
2.054	1.2267	4600	2.4345
2.0565	1.28	4800	2.4241
2.0422	1.3333	5000	2.4216
2.0363	1.3867	5200	2.4154
2.0205	1.44	5400	2.4081
2.0379	1.4933	5600	2.4040
2.0518	1.5467	5800	2.3963
2.0322	1.6	6000	2.3875
1.9886	1.6533	6200	2.3835
2.021	1.7067	6400	2.3803
2.0979	1.76	6600	2.3744
1.9945	1.8133	6800	2.3707
2.0038	1.8667	7000	2.3663
1.9908	1.92	7200	2.3624
1.9838	1.9733	7400	2.3586
1.8927	2.0267	7600	2.3825
1.8222	2.08	7800	2.3888
1.7761	2.1333	8000	2.3876
1.7677	2.1867	8200	2.3885
1.7719	2.24	8400	2.3886
1.7554	2.2933	8600	2.3890
1.7759	2.3467	8800	2.3844
1.7986	2.4	9000	2.3826
1.7972	2.4533	9200	2.3825
1.7806	2.5067	9400	2.3822
1.7852	2.56	9600	2.3818
1.7731	2.6133	9800	2.3808
1.7871	2.6667	10000	2.3800
1.8065	2.7200	10200	2.3795
1.735	2.7733	10400	2.3795
1.779	2.8267	10600	2.3790
1.7599	2.88	10800	2.3790
1.7892	2.9333	11000	2.3790
1.774	2.9867	11200	2.3790

Framework versions

Transformers 4.56.2
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 82

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for valer125/business-news-generator

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(945)

this model