Instructions to use Dimeltech/Tenezis-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dimeltech/Tenezis-8B with Transformers:

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

pipe = pipeline("text-generation", model="Dimeltech/Tenezis-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Dimeltech/Tenezis-8B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dimeltech/Tenezis-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dimeltech/Tenezis-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dimeltech/Tenezis-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dimeltech/Tenezis-8B

SGLang

How to use Dimeltech/Tenezis-8B 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 "Dimeltech/Tenezis-8B" \
    --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": "Dimeltech/Tenezis-8B",
		"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 "Dimeltech/Tenezis-8B" \
        --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": "Dimeltech/Tenezis-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Dimeltech/Tenezis-8B 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 Dimeltech/Tenezis-8B 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 Dimeltech/Tenezis-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Dimeltech/Tenezis-8B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Dimeltech/Tenezis-8B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Dimeltech/Tenezis-8B with Docker Model Runner:
```
docker model run hf.co/Dimeltech/Tenezis-8B
```

Tenezis-8B / README.md

Therence-NG

changes

3d98d4c verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

2.08 kB

	---
	base_model: unsloth/llama-3-8b-bnb-4bit
	license: apache-2.0
	language:
	- zu
	- wo
	- sw
	- ha
	- am
	- yo
	- xh
	- sn
	- ar
	tags:
	- text-generation
	- multilingual
	- african-languages
	- transformers
	- unsloth
	- llama
	- trl
	---

	# Tenezis-8b: Multilingual Model for Africa

	## Overview

	Tenezis-8b is an AI model developed by Dimeltech, specifically designed to include and value African languages. This model is based on `unsloth/llama-3-8b-bnb-4bit` and has been fine-tuned for fast and efficient text generation.

	## Features

	- Base Model: `unsloth/llama-3-8b-bnb-4bit`
	- Number of Parameters: 8 billion
	- License: Apache 2.0
	- Supported Languages: English, Zulu, Wolof, Swahili, Hausa, Amharic, Yoruba, Xhosa, Shona, and Arabic.
	- Technologies Used:
	- [Unsloth](https://github.com/unslothai/unsloth) for rapid training optimization
	- [Transformers](https://huggingface.co/transformers/) by Hugging Face for language model management
	- [TRL (Transformers Reinforcement Learning)](https://github.com/huggingface/trl) for reinforcement fine-tuning

	## Developed by Dimeltech

	Dimeltech is a company dedicated to technological innovation and digital inclusion, with a particular focus on Africa. Our mission is to make artificial intelligence technologies accessible and beneficial to everyone.

	## License

	This model is distributed under the Apache 2.0 license, allowing for flexible and open use while ensuring transparency and collaborative development.

	## Contribution and Support

	We encourage community contributions to enhance and expand the capabilities of Tenezis-8b. For more information on contributing, please refer to our [contribution guide](https://github.com/dimeltech/tenezis-8b/contributing).

	For any support or questions, please contact our team via our [GitHub page](https://github.com/dimeltech/tenezis-8b) or through our [community forum](https://community.dimeltech.com).

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)