ai4bharat / Airavata

huggingface.co
Total runs: 1.1K
24-hour runs: 1
7-day runs: -73
30-day runs: -3.1K
Model's Last Updated: 3月 11 2024
text-generation

Introduction of Airavata

Model Details of Airavata

Airavata

This model is a 7B OpenHathi model finetuned on IndicInstruct dataset which is a collection of instruction datasets (Anudesh, wikiHow, Flan v2, Dolly, Anthropic-HHH, OpenAssistant v1, and LymSys-Chat). Please check the corresponding huggingface dataset card for more details.

This was trained as part of the technical report Airavata: Introducing Hindi Instruction-tuned LLM . The codebase used to train and evaluate this model can be found at https://github.com/AI4Bharat/IndicInstruct .

Usage

Clone https://github.com/AI4Bharat/IndicInstruct and install the required dependencies. Then download or clone this model to the same machine.

Input Format

The model is trained to use the chat format similar to open-instruct code repository (note the newlines):

<|user|>
Your message here!
<|assistant|>

For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|> , this can affect generation quality quite a bit.

Hyperparameters

We fine-tune OpenHathi base model on the aforementioned IndicInstruct dataset with LoRA. The hyperparameters for the LoRA fine-tuning are listed below:

  • LoRA Rank: 16
  • LoRA alpha: 32
  • LoRA Dropout: 0.05
  • LoRA Target Modules: ["q_proj", "v_proj", "k_proj", "down_proj", "gate_proj", "up_proj"]
  • Epochs: 4
  • Learning rate: 5e-4
  • Batch Size: 128
  • Floating Point Precision: bfloat16

We recommend the readers to check out our official blog post for more details on the model training, ablations and evaluation results.

Example
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

device = "cuda" if torch.cuda.is_available() else "cpu"


def create_prompt_with_chat_format(messages, bos="<s>", eos="</s>", add_bos=True):
    formatted_text = ""
    for message in messages:
        if message["role"] == "system":
            formatted_text += "<|system|>\n" + message["content"] + "\n"
        elif message["role"] == "user":
            formatted_text += "<|user|>\n" + message["content"] + "\n"
        elif message["role"] == "assistant":
            formatted_text += "<|assistant|>\n" + message["content"].strip() + eos + "\n"
        else:
            raise ValueError(
                "Tulu chat template only supports 'system', 'user' and 'assistant' roles. Invalid role: {}.".format(
                    message["role"]
                )
            )
    formatted_text += "<|assistant|>\n"
    formatted_text = bos + formatted_text if add_bos else formatted_text
    return formatted_text


def inference(input_prompts, model, tokenizer):
    input_prompts = [
        create_prompt_with_chat_format([{"role": "user", "content": input_prompt}], add_bos=False)
        for input_prompt in input_prompts
    ]

    encodings = tokenizer(input_prompts, padding=True, return_tensors="pt")
    encodings = encodings.to(device)

    with torch.inference_mode():
        outputs = model.generate(encodings.input_ids, do_sample=False, max_new_tokens=250)

    output_texts = tokenizer.batch_decode(outputs.detach(), skip_special_tokens=True)

    input_prompts = [
        tokenizer.decode(tokenizer.encode(input_prompt), skip_special_tokens=True) for input_prompt in input_prompts
    ]
    output_texts = [output_text[len(input_prompt) :] for input_prompt, output_text in zip(input_prompts, output_texts)]
    return output_texts


model_name = "ai4bharat/Airavata"

tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")
tokenizer.pad_token = tokenizer.eos_token
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)

input_prompts = [
    "मैं अपने समय प्रबंधन कौशल को कैसे सुधार सकता हूँ? मुझे पांच बिंदु बताएं।",
    "मैं अपने समय प्रबंधन कौशल को कैसे सुधार सकता हूँ? मुझे पांच बिंदु बताएं और उनका वर्णन करें।",
]
outputs = inference(input_prompts, model, tokenizer)
print(outputs)
Citation
@article{gala2024airavata,
  title   = {Airavata: Introducing Hindi Instruction-tuned LLM},
  author  = {Jay Gala and Thanmay Jayakumar and Jaavid Aktar Husain and Aswanth Kumar M and Mohammed Safi Ur Rahman Khan and Diptesh Kanojia and Ratish Puduppully and Mitesh M. Khapra and Raj Dabre and Rudra Murthy and Anoop Kunchukuttan},
  year    = {2024},
  journal = {arXiv preprint arXiv: 2401.15006}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 45.52
AI2 Reasoning Challenge (25-Shot) 46.50
HellaSwag (10-Shot) 69.26
MMLU (5-Shot) 43.90
TruthfulQA (0-shot) 40.62
Winogrande (5-shot) 68.82
GSM8k (5-shot) 4.02

Runs of ai4bharat Airavata on huggingface.co

1.1K
Total runs
1
24-hour runs
-76
3-day runs
-73
7-day runs
-3.1K
30-day runs

More Information About Airavata huggingface.co Model

More Airavata license Visit here:

https://choosealicense.com/licenses/llama2

Airavata huggingface.co

Airavata huggingface.co is an AI model on huggingface.co that provides Airavata's model effect (), which can be used instantly with this ai4bharat Airavata model. huggingface.co supports a free trial of the Airavata model, and also provides paid use of the Airavata. Support call Airavata model through api, including Node.js, Python, http.

ai4bharat Airavata online free

Airavata huggingface.co is an online trial and call api platform, which integrates Airavata's modeling effects, including api services, and provides a free online trial of Airavata, you can try Airavata online for free by clicking the link below.

ai4bharat Airavata online free url in huggingface.co:

https://huggingface.co/ai4bharat/Airavata

Airavata install

Airavata is an open source model from GitHub that offers a free installation service, and any user can find Airavata on GitHub to install. At the same time, huggingface.co provides the effect of Airavata install, users can directly use Airavata installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Airavata install url in huggingface.co:

https://huggingface.co/ai4bharat/Airavata

Url of Airavata

Provider of Airavata huggingface.co

ai4bharat
ORGANIZATIONS

Other API from ai4bharat

huggingface.co

Total runs: 1.1M
Run Growth: 781.3K
Growth Rate: 67.72%
Updated: 8月 07 2022
huggingface.co

Total runs: 47.7K
Run Growth: 3.2K
Growth Rate: 6.71%
Updated: 12月 21 2022
huggingface.co

Total runs: 1.8K
Run Growth: 350
Growth Rate: 19.84%
Updated: 8月 07 2022
huggingface.co

Total runs: 222
Run Growth: -81
Growth Rate: -23.62%
Updated: 10月 18 2024
huggingface.co

Total runs: 8
Run Growth: -3
Growth Rate: -11.54%
Updated: 10月 18 2024