Instructions to use GodsonNtungi/swahilillama3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GodsonNtungi/swahilillama3-8b with Transformers:

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

pipe = pipeline("text-generation", model="GodsonNtungi/swahilillama3-8b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GodsonNtungi/swahilillama3-8b")
model = AutoModelForCausalLM.from_pretrained("GodsonNtungi/swahilillama3-8b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GodsonNtungi/swahilillama3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GodsonNtungi/swahilillama3-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GodsonNtungi/swahilillama3-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GodsonNtungi/swahilillama3-8b

SGLang

How to use GodsonNtungi/swahilillama3-8b 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 "GodsonNtungi/swahilillama3-8b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GodsonNtungi/swahilillama3-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "GodsonNtungi/swahilillama3-8b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GodsonNtungi/swahilillama3-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use GodsonNtungi/swahilillama3-8b 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 GodsonNtungi/swahilillama3-8b 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 GodsonNtungi/swahilillama3-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GodsonNtungi/swahilillama3-8b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="GodsonNtungi/swahilillama3-8b",
    max_seq_length=2048,
)

Docker Model Runner
How to use GodsonNtungi/swahilillama3-8b with Docker Model Runner:
```
docker model run hf.co/GodsonNtungi/swahilillama3-8b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Swahili llama 3 8b

Developed by: GodsonNtungi
License: apache-2.0
Finetuned from model : unsloth/llama-3-8b-bnb-4bit

An experimental model with poor performing results, but a great start

training run : 1 epoch
time: 9 hours : 20 mins : 07 seconds
training loss: 0.8683

PEFT parameters

model = FastLanguageModel.get_peft_model(
    model,
    r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 16,
    lora_dropout = 0, # Supports any, but = 0 is optimized
    bias = "none",    # Supports any, but = "none" is optimized
    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
    random_state = 3407,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
)

Weakness
The model is not properly finetuned to generate end of text token when needed , hence great results start followed by gibberish depending on max token limit set

Downloads last month: 7

Model tree for GodsonNtungi/swahilillama3-8b

Quantizations

1 model

GodsonNtungi
/

swahilillama3-8b

Swahili llama 3 8b

Model tree for GodsonNtungi/swahilillama3-8b

Dataset used to train GodsonNtungi/swahilillama3-8b