Instructions to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with Transformers:

# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("translation", model="suyash2739/English_to_Hinglish_cmu_hinglish_dog")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("suyash2739/English_to_Hinglish_cmu_hinglish_dog", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog: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 suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog: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 suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M

Use Docker

docker model run hf.co/suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M

LM Studio
Jan
Ollama
How to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with Ollama:
```
ollama run hf.co/suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with Docker Model Runner:
```
docker model run hf.co/suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M
```

Lemonade

How to use suyash2739/English_to_Hinglish_cmu_hinglish_dog with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull suyash2739/English_to_Hinglish_cmu_hinglish_dog:Q4_K_M

Run and chat with the model

lemonade run user.English_to_Hinglish_cmu_hinglish_dog-Q4_K_M

List all available models

lemonade list

Atomic Chat

Llama 3 8B — English → Hinglish (CMU Hinglish DoG variant)

An earlier variant of my English → Hinglish translation work: Llama 3 8B Instruct fine-tuned with QLoRA on a cleaned version of the CMU Hinglish DoG conversational dataset.

Looking for the recommended model? The newer variant trained on a curated news-domain corpus produces more fluent Hinglish: English_to_Hinglish_fintuned_lamma_3_8b_instruct.

Details

Base model: unsloth/llama-3-8b-Instruct-bnb-4bit
Method: QLoRA (4-bit) with Unsloth + HuggingFace TRL
Training data: suyash2739/Hinglish — cleaned from cmu_hinglish_dog (conversational domain)
License: Apache 2.0

How to use

Same interface as the main model:

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="suyash2739/English_to_Hinglish_cmu_hinglish_dog",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,
)

Prompt format: Translate the input from English to Hinglish to give the response. followed by ### Input: and ### Response: sections.

Why two variants?

This model captures conversational, dialogue-style Hinglish (CMU DoG is a document-grounded conversation dataset), while the main model targets news-register Hinglish. Comparing the two illustrates how strongly domain of the parallel corpus shapes code-mixing style in the output.

Limitations

Conversational-domain training data; formal text may translate awkwardly.
Romanized Hinglish only.
Inherits base-model and corpus biases.

Downloads last month: 113

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Model tree for suyash2739/English_to_Hinglish_cmu_hinglish_dog

Base model

unsloth/llama-3-8b-Instruct-bnb-4bit

Adapter

(182)

this model

Datasets used to train suyash2739/English_to_Hinglish_cmu_hinglish_dog

Collection including suyash2739/English_to_Hinglish_cmu_hinglish_dog

Hinglish & Code-Switched NLP

Collection

Llama 3 8B LoRA models + parallel corpora for English→Hinglish code-switched translation. • 4 items • Updated Jul 15