Instructions to use pranavajay/hindi-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pranavajay/hindi-8b with Transformers:

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

pipe = pipeline("text-generation", model="pranavajay/hindi-8b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pranavajay/hindi-8b")
model = AutoModelForCausalLM.from_pretrained("pranavajay/hindi-8b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pranavajay/hindi-8b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pranavajay/hindi-8b

SGLang

How to use pranavajay/hindi-8b 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 "pranavajay/hindi-8b" \
    --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": "pranavajay/hindi-8b",
		"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 "pranavajay/hindi-8b" \
        --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": "pranavajay/hindi-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pranavajay/hindi-8b with Docker Model Runner:
```
docker model run hf.co/pranavajay/hindi-8b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

pranavajay/hindi-8b

Overview

🌟 Introducing the "pranavajay/hindi-8b" model, a text generator language model specifically fine-tuned for Hindi language conversational tasks. This model is designed to engage in fluent and contextually relevant conversations, making it an ideal tool for chatbots, language translation, and more.

Model Details

Base Model: A robust pre-trained language model, adapted for Hindi.
Fine-Tuning: The model has been further fine-tuned on a diverse dataset of Hindi conversations to enhance its conversational capabilities.
Language Support: Primarily Hindi, with the ability to understand and respond in contextually appropriate English when necessary.
Model Size: 10.2B parameters for rich and nuanced responses.
Usage: Ideal for building interactive AI applications that require natural language understanding and generation in Hindi.

Quick Start

To use the "pranavajay/hindi-8b" model with the Hugging Face Transformers library, follow these steps:

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("pranavajay/hindi-8b")
model = AutoModelForCausalLM.from_pretrained("pranavajay/hindi-8b")

# Example conversation
input_text = "हमारे देश का नवाब कौन है?"
input_ids = tokenizer.encode(input_text, return_tensors="pt")
output = model.generate(input_ids, max_length=50, num_return_sequences=1)

# Decode the response
response = tokenizer.decode(output[0], skip_special_tokens=True)
print(response)

Training The "pranavajay/hindi-8b" model was trained using a combination of supervised learning and reinforcement learning techniques. The training dataset consisted of a wide range of Hindi conversations, including dialogues from various domains such as customer service, education, and entertainment.

License The "pranavajay/hindi-8b" model is released under the Apache License 2.0. Please review the license for details regarding the use, modification, and distribution of the model.

Citation If you use the "pranavajay/hindi-8b" model in your research or applications, please cite it as follows:

bibtex

@misc{hindi-8b,
  author = {Pranav Ajay},
  title = {Hindi Chat 8B Model},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face Model Repository},
  howpublished = {\url{https://huggingface.co/pranavajay/hindi-chat-8b}}
}

Feedback and Support For any questions, feedback, or support regarding the "pranavajay/hindi-chat-8b" model, please contact us at pranavajay74@gmail.com

Downloads last month: -

Safetensors

Model size

11B params

Tensor type

F16

Model tree for pranavajay/hindi-8b

Quantizations

1 model