Bharat-Tiny-LLM-v2 API & Inference Endpoint

🎯 Model Overview

Bharat-Tiny-LLM v2 is an open-weights 1.5B parameter language model built on top of Qwen2.5-1.5B, optimized specifically for Hindi and Hinglish text generation.

By introducing Brahmi Token Injection — a technique that surgically injects 300 Devanagari subword tokens into the model's vocabulary — Bharat-Tiny-LLM v2 eliminates the severe "Token Tax" imposed by standard English-centric tokenizers on Indian scripts.

This repository contains the unquantized PyTorch / HuggingFace Transformers open weights, compatible with Linux, Windows, CUDA GPUs, vLLM, TGI, and Google Colab.

🎨 Architectural Pipeline & Training Methodology

Brahmi Token Injection Architecture

Interactive Training Pipeline Flowchart

mermaid
flowchart LR
    A["Raw Hindi Corpus"] --> B["Brahmi Subword Mining<br>(Top 300 Devanagari Tokens)"]
    B --> C["Tokenizer Vocabulary Expansion<br>(151,936 ➔ 152,236)"]
    C --> D["Stage 1: Embedding Alignment<br>(Freeze Backbone, Train 300 Embeddings)"]
    D --> E["Stage 2: LoRA Fine-Tuning<br>(Rank=16 on Attention q,k,v,o proj)"]
    E --> F["Fused PyTorch Base Weights<br>(eulogik/Bharat-Tiny-LLM-v2)"]
    F --> G["Q4 Affine Quantization<br>(eulogik/Bharat-Tiny-LLM-v2-MLX)"]

✨ Key Benchmarks & Technical Advantages

Table with columns: Metric, Base Qwen2.5-1.5B, Bharat-Tiny-LLM v2, Technical Advantage
Metric	Base Qwen2.5-1.5B	Bharat-Tiny-LLM v2	Technical Advantage
Tokens for 1,000 Hindi Chars	~950 tokens	~630 tokens	33.8% Fewer Tokens (up to 58% on chat prompts)
Inference Throughput (Hindi)	50 tok/s	68 tok/s	+36% Speed Boost
Validation Loss (Hindi Corpus)	2.776	1.837	52.5% Loss Reduction (Perplexity: 16.1 → 6.3)
Hardware Compatibility	CUDA / CPU / MPS	CUDA / CPU / MPS	Universal PyTorch / vLLM / GGUF support

🚀 Quick Start with PyTorch & Transformers

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "eulogik/Bharat-Tiny-LLM-v2"

# Load Tokenizer & Model Weights
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Generate Hindi Text
prompt = "भारत की सांस्कृतिक विविधता के बारे में बताइए:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.7,
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📊 Token Compression Benchmarks

Table with columns: Prompt (Hindi / Hinglish), Base Qwen Tokens, Bharat-v2 Tokens, Savings
Prompt (Hindi / Hinglish)	Base Qwen Tokens	Bharat-v2 Tokens	Savings
`"ज़रूरी बात है क्या करते हो"`	26 tokens	11 tokens	58% Savings
`"नमस्ते, आप कैसे हैं?"`	15 tokens	7 tokens	53% Savings
`"भारत की राजधानी नई दिल्ली है"`	22 tokens	14 tokens

🔗 Model Family Repositories

Apple Silicon MLX Quantized (880MB): eulogik/Bharat-Tiny-LLM-v2-MLX
GGUF / llama.cpp: eulogik/Bharat-Tiny-LLM-GGUF

📜 License & Citation

Licensed under Apache 2.0. Free for commercial, enterprise, and research use.

bibtex
@misc{kishore2026brahmi,
    title={Brahmi: Efficient Devanagari Token Injection for Multilingual LLMs},
    author={Gautam Kishore},
    year={2026},
    publisher={eulogik},
    howpublished={\url{https://huggingface.co/eulogik/Bharat-Tiny-LLM-v2}}
}

mermaid

flowchart LR
    A["Raw Hindi Corpus"] --> B["Brahmi Subword Mining<br>(Top 300 Devanagari Tokens)"]
    B --> C["Tokenizer Vocabulary Expansion<br>(151,936 ➔ 152,236)"]
    C --> D["Stage 1: Embedding Alignment<br>(Freeze Backbone, Train 300 Embeddings)"]
    D --> E["Stage 2: LoRA Fine-Tuning<br>(Rank=16 on Attention q,k,v,o proj)"]
    E --> F["Fused PyTorch Base Weights<br>(eulogik/Bharat-Tiny-LLM-v2)"]
    F --> G["Q4 Affine Quantization<br>(eulogik/Bharat-Tiny-LLM-v2-MLX)"]

Metric

Base Qwen2.5-1.5B

Bharat-Tiny-LLM v2

Technical Advantage

Tokens for 1,000 Hindi Chars

~950 tokens

~630 tokens

33.8% Fewer Tokens (up to 58% on chat prompts)

Inference Throughput (Hindi)

50 tok/s

68 tok/s

+36% Speed Boost

Validation Loss (Hindi Corpus)

2.776

1.837

52.5% Loss Reduction (Perplexity: 16.1 → 6.3)

Hardware Compatibility

CUDA / CPU / MPS

Universal PyTorch / vLLM / GGUF support

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "eulogik/Bharat-Tiny-LLM-v2"

# Load Tokenizer & Model Weights
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Generate Hindi Text
prompt = "भारत की सांस्कृतिक विविधता के बारे में बताइए:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.7,
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Prompt (Hindi / Hinglish)

Base Qwen Tokens

Bharat-v2 Tokens

Savings

"ज़रूरी बात है क्या करते हो"

26 tokens

11 tokens

58% Savings

"नमस्ते, आप कैसे हैं?"

15 tokens

7 tokens

53% Savings

"भारत की राजधानी नई दिल्ली है"

22 tokens

14 tokens

bibtex

@misc{kishore2026brahmi,
    title={Brahmi: Efficient Devanagari Token Injection for Multilingual LLMs},
    author={Gautam Kishore},
    year={2026},
    publisher={eulogik},
    howpublished={\url{https://huggingface.co/eulogik/Bharat-Tiny-LLM-v2}}
}

Bharat-Tiny-LLM-v2

README

🎯 Model Overview

🎨 Architectural Pipeline & Training Methodology

Interactive Training Pipeline Flowchart

✨ Key Benchmarks & Technical Advantages

🚀 Quick Start with PyTorch & Transformers

📊 Token Compression Benchmarks

🔗 Model Family Repositories

📜 License & Citation

Explore FriendliAI today

README

🎯 Model Overview

🎨 Architectural Pipeline & Training Methodology

Interactive Training Pipeline Flowchart

✨ Key Benchmarks & Technical Advantages

🚀 Quick Start with PyTorch & Transformers

📊 Token Compression Benchmarks

🔗 Model Family Repositories

📜 License & Citation