Instructions to use mwitiderrick/SwahiliGPT_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mwitiderrick/SwahiliGPT_v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="mwitiderrick/SwahiliGPT_v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliGPT_v0.1")
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliGPT_v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mwitiderrick/SwahiliGPT_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mwitiderrick/SwahiliGPT_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mwitiderrick/SwahiliGPT_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mwitiderrick/SwahiliGPT_v0.1

SGLang

How to use mwitiderrick/SwahiliGPT_v0.1 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 "mwitiderrick/SwahiliGPT_v0.1" \
    --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": "mwitiderrick/SwahiliGPT_v0.1",
		"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 "mwitiderrick/SwahiliGPT_v0.1" \
        --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": "mwitiderrick/SwahiliGPT_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mwitiderrick/SwahiliGPT_v0.1 with Docker Model Runner:
```
docker model run hf.co/mwitiderrick/SwahiliGPT_v0.1
```

SwahiliGPT

This is a Mistral model that has been fine-tuned on the Wikipedia Swahili dataset.

Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliGPT_v0.1")
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliGPT_v0.1", device_map="auto")
inputs = tokenizer("Hapo zamani za kale", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200,  do_sample=True, repetition_penalty=1.1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))


"""
Hapo zamani za kale katika historia ya jamii, ambavyo sehemu moja hutazama historia ile inayopendekezwa au inayojulikana, na sehemu nyingine inafanya history  ambalai hainajulikana. 
Utaifishaji unaleta utata kwanza mambo ya karne zilizoandamana, na seconda matokeo yanatokana na vipitio vya maisha muhimu ambavyo haivyo vitakuva mahitaji katika jamii hiyo (hunajua wakiweka mitindo katakatani). Ni kinyume kingine kwamba kuna sifa ambayo umechukizwa vitu hivi vilitengenezwa zaidi.

Katika Afrika Magharibi, historia huitwa ngan
"""

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

F16

Model tree for mwitiderrick/SwahiliGPT_v0.1

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(942)

this model

mwitiderrick
/

SwahiliGPT_v0.1

SwahiliGPT

Usage

Model tree for mwitiderrick/SwahiliGPT_v0.1

Dataset used to train mwitiderrick/SwahiliGPT_v0.1