Instructions to use RichardErkhov/Someman_-_bart-hindi-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Someman_-_bart-hindi-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/Someman_-_bart-hindi-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/Someman_-_bart-hindi-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/Someman_-_bart-hindi-8bits", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichardErkhov/Someman_-_bart-hindi-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/Someman_-_bart-hindi-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/Someman_-_bart-hindi-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/Someman_-_bart-hindi-8bits

SGLang

How to use RichardErkhov/Someman_-_bart-hindi-8bits 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 "RichardErkhov/Someman_-_bart-hindi-8bits" \
    --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": "RichardErkhov/Someman_-_bart-hindi-8bits",
		"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 "RichardErkhov/Someman_-_bart-hindi-8bits" \
        --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": "RichardErkhov/Someman_-_bart-hindi-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/Someman_-_bart-hindi-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Someman_-_bart-hindi-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

bart-hindi - bnb 8bits

Model creator: https://huggingface.co/Someman/
Original model: https://huggingface.co/Someman/bart-hindi/

Original model description:

license: apache-2.0 tags: - generated_from_trainer - hindi - summarization - seq2seq datasets: - Someman/hindi-summarization base_model: facebook/bart-base model-index: - name: bart-hindi results: []

bart-hindi

This model is a fine-tuned version of facebook/bart-base on the Someman/hindi-summarization dataset. It achieves the following results on the evaluation set:

Loss: 0.4985

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.6568	0.14	500	0.6501
0.682	0.29	1000	0.5757
0.5331	0.43	1500	0.5530
0.5612	0.58	2000	0.5311
0.5685	0.72	2500	0.5043
0.4993	0.87	3000	0.4985

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Downloads last month: 4

Safetensors

Model size

96.2M params

Tensor type

F32

F16