Instructions to use Noxus09/code-mixed-translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Noxus09/code-mixed-translation with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Noxus09/code-mixed-translation",
	filename="unsloth.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Noxus09/code-mixed-translation with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Noxus09/code-mixed-translation:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Noxus09/code-mixed-translation:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Noxus09/code-mixed-translation:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Noxus09/code-mixed-translation:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Noxus09/code-mixed-translation:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Noxus09/code-mixed-translation:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Noxus09/code-mixed-translation:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Noxus09/code-mixed-translation:Q4_K_M

Use Docker

docker model run hf.co/Noxus09/code-mixed-translation:Q4_K_M

LM Studio
Jan
Ollama
How to use Noxus09/code-mixed-translation with Ollama:
```
ollama run hf.co/Noxus09/code-mixed-translation:Q4_K_M
```

Unsloth Studio

How to use Noxus09/code-mixed-translation with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Noxus09/code-mixed-translation to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Noxus09/code-mixed-translation to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Noxus09/code-mixed-translation to start chatting

Atomic Chat new
Docker Model Runner
How to use Noxus09/code-mixed-translation with Docker Model Runner:
```
docker model run hf.co/Noxus09/code-mixed-translation:Q4_K_M
```

Lemonade

How to use Noxus09/code-mixed-translation with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Noxus09/code-mixed-translation:Q4_K_M

Run and chat with the model

lemonade run user.code-mixed-translation-Q4_K_M

List all available models

lemonade list

Improved Code-Mixed Sentence Translation Using Decoder-Only Transformers

Overview

This project addresses the limitations of traditional Neural Machine Translation (NMT) models in translating code-mixed sentences by utilizing a decoder-only transformer model. Inspired by the training methodologies of models like GPT and Llama, this approach leverages self-supervised learning to understand the context of languages more deeply. After learning the context, the model is fine-tuned on a smaller translation dataset, making it effective for translating both regular and code-mixed sentences.

Benefits

Fraction of Translation Dataset: The model requires only a small amount of translation data for fine-tuning, which reduces the data preparation overhead.
Rich and Meaningful Translation: By understanding the underlying context of languages, the model provides more accurate and meaningful translations for both regular and code-mixed sentences.
Multilingual Capability: A single model can potentially translate multiple languages, making it a versatile solution for diverse translation needs.

Approach

Context Learning: Train a decoder-only transformer model on a large corpus of text using self-supervised learning. This stage allows the model to grasp the contextual nuances of different languages.
Fine-Tuning: Fine-tune the pre-trained model on a smaller dataset specifically for translation tasks. This step adapts the model to effectively handle translation while retaining its contextual understanding.

Example

Here is a comparison between the traditional Google Translate and the proposed approach:

Text: “Sun ka diameter kya hoga?”
Google Translate: “what will happen to sun's demetre”

Proposed Approach: “What is the diameter of the Sun?”

The proposed method outperforms traditional translation models by providing a more accurate translation that respects the context and meaning of the original sentence.

Usage

Pre-training: Train the decoder-only transformer model on a large text corpus.
Fine-tuning: Fine-tune the model on a smaller dataset of translated sentences.
Translation: Use the fine-tuned model to translate both regular and code-mixed sentences.

Future Work

Evaluation: Conduct thorough evaluations and comparisons with other state-of-the-art translation models.
Expansion: Explore additional languages and code-mixed scenarios to enhance the model's versatility.

License

This project is licensed under the MIT License.

Feel free to adjust any sections as needed!

Downloads last month: -

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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