Instructions to use mgr-gaurav/nepali_caption_model_output_25 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgr-gaurav/nepali_caption_model_output_25 with Transformers:

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

pipe = pipeline("image-text-to-text", model="mgr-gaurav/nepali_caption_model_output_25")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mgr-gaurav/nepali_caption_model_output_25")
model = AutoModelForMultimodalLM.from_pretrained("mgr-gaurav/nepali_caption_model_output_25", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mgr-gaurav/nepali_caption_model_output_25 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgr-gaurav/nepali_caption_model_output_25"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgr-gaurav/nepali_caption_model_output_25",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mgr-gaurav/nepali_caption_model_output_25

SGLang

How to use mgr-gaurav/nepali_caption_model_output_25 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 "mgr-gaurav/nepali_caption_model_output_25" \
    --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": "mgr-gaurav/nepali_caption_model_output_25",
		"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 "mgr-gaurav/nepali_caption_model_output_25" \
        --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": "mgr-gaurav/nepali_caption_model_output_25",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mgr-gaurav/nepali_caption_model_output_25 with Docker Model Runner:
```
docker model run hf.co/mgr-gaurav/nepali_caption_model_output_25
```

nepali_caption_model_output_25

This model is a fine-tuned version of Salesforce/blip-image-captioning-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2972

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: 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: linear
num_epochs: 25
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2958	1.0	225	1.0108
1.0094	2.0	450	0.8830
0.8718	3.0	675	0.8173
0.7440	4.0	900	0.7839
0.6971	5.0	1125	0.7930
0.6160	6.0	1350	0.7889
0.5226	7.0	1575	0.8216
0.4363	8.0	1800	0.8534
0.3499	9.0	2025	0.8852
0.2907	10.0	2250	0.9386
0.2399	11.0	2475	0.9677
0.2000	12.0	2700	1.0079
0.1731	13.0	2925	1.0467
0.1538	14.0	3150	1.0645
0.1369	15.0	3375	1.0913
0.1218	16.0	3600	1.1158
0.1083	17.0	3825	1.1491
0.0960	18.0	4050	1.1737
0.0805	19.0	4275	1.1663
0.0695	20.0	4500	1.1948
0.0531	21.0	4725	1.2455
0.0380	22.0	4950	1.2512
0.0252	23.0	5175	1.2791
0.0199	24.0	5400	1.2940
0.0154	25.0	5625	1.2972

Framework versions

Transformers 5.13.1
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 11

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mgr-gaurav/nepali_caption_model_output_25

Base model

Salesforce/blip-image-captioning-base

Finetuned

(59)

this model