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

Libraries

How to use Bennerdo/rieko with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-pt")
model = PeftModel.from_pretrained(base_model, "Bennerdo/rieko")

Transformers

How to use Bennerdo/rieko with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Bennerdo/rieko", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bennerdo/rieko with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Bennerdo/rieko

SGLang

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

Docker Model Runner
How to use Bennerdo/rieko with Docker Model Runner:
```
docker model run hf.co/Bennerdo/rieko
```

Bennerdo commited on 4 days ago

Commit

16c662f

verified ·

1 Parent(s): d27fbb5

update readme

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -66,8 +66,8 @@ The adapter was trained in two stages with QLoRA:
 ## Bias, Risks, and Limitations
 - **Small model:** at 1B parameters, the model has limited reasoning ability and makes factual errors and hallucinations.
-- **Unreviewed synthetic data:** part of the SFT data was generated by Gemini, and the identity and greeting examples were written from templates. A native speaker has not yet reviewed them, so the output can contain unnatural phrasing or spelling errors.
-- **Domain skew:** the translation data is weighted towards religious (Bible) and OPUS text. Caps reduce this skew but do not remove it.
 - **Dialect:** the training data favours Kenyan Nyanza Dholuo. The model is not tuned to other Luo varieties.
 - **Code-switching:** the model sometimes mixes in English or Swahili.

 ## Bias, Risks, and Limitations
 - **Small model:** at 1B parameters, the model has limited reasoning ability and makes factual errors and hallucinations.
+- **Synthetic data:** part of the SFT data was generated by Gemini, and the identity and greeting examples were written from templates. A native Dholuo speaker (the author) reviewed this data and found almost all of it correct. A few unnatural phrasings or spelling errors may remain.
+- - **Domain skew:** the translation data is weighted towards religious (Bible) and OPUS text. Caps reduce this skew but do not remove it.
 - **Dialect:** the training data favours Kenyan Nyanza Dholuo. The model is not tuned to other Luo varieties.
 - **Code-switching:** the model sometimes mixes in English or Swahili.