Instructions to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt with Transformers:

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

pipe = pipeline("text-generation", model="KickItLikeShika/llama-3.3-70B-Instruct-en-tt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KickItLikeShika/llama-3.3-70B-Instruct-en-tt")
model = AutoModelForCausalLM.from_pretrained("KickItLikeShika/llama-3.3-70B-Instruct-en-tt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KickItLikeShika/llama-3.3-70B-Instruct-en-tt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KickItLikeShika/llama-3.3-70B-Instruct-en-tt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KickItLikeShika/llama-3.3-70B-Instruct-en-tt

SGLang

How to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt 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 "KickItLikeShika/llama-3.3-70B-Instruct-en-tt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KickItLikeShika/llama-3.3-70B-Instruct-en-tt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "KickItLikeShika/llama-3.3-70B-Instruct-en-tt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KickItLikeShika/llama-3.3-70B-Instruct-en-tt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt 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 KickItLikeShika/llama-3.3-70B-Instruct-en-tt 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 KickItLikeShika/llama-3.3-70B-Instruct-en-tt to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KickItLikeShika/llama-3.3-70B-Instruct-en-tt to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="KickItLikeShika/llama-3.3-70B-Instruct-en-tt",
    max_seq_length=2048,
)

Docker Model Runner
How to use KickItLikeShika/llama-3.3-70B-Instruct-en-tt with Docker Model Runner:
```
docker model run hf.co/KickItLikeShika/llama-3.3-70B-Instruct-en-tt
```

Llama 70b English to Tatar Translation (Synthetic Data)

Developed by: KickItLikeShika
License: apache-2.0
Finetuned from model : unsloth/llama-3.3-70b-instruct-unsloth-bnb-4bit

Model was trained as part of Low Resource Machine Translation Workshop (EACL26) https://www.loresmt.org/

The model was trained on a new synthetic dataset introduced as part of my research on the workshop

Training data: https://huggingface.co/datasets/KickItLikeShika/english-tatar-translation

Citation

@inproceedings{khamis-2026-navigating,
    title = "Navigating Data Scarcity in Low-Resource {E}nglish-{T}atar Translation using {LLM} Fine-Tuning",
    author = "Khamis, Ahmed Khaled",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-hong  and
      Vylomova, Ekaterina  and
      Pirinen, Flammie  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Zhao, Xiaobing",
    booktitle = "Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages ({L}o{R}es{MT} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.loresmt-1.16/",
    pages = "198--202",
    ISBN = "979-8-89176-366-1"
}

Downloads last month: 4

Safetensors

Model size

71B params

Tensor type

BF16

Collection including KickItLikeShika/llama-3.3-70B-Instruct-en-tt

Navigating Data Scarcity

Collection

Data and model of Navigating Data Scarcity paper • 2 items • Updated Apr 13