Instructions to use ipswy/senti-shujaa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ipswy/senti-shujaa with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ipswy/senti-shujaa")
model = AutoModelForCausalLM.from_pretrained("ipswy/senti-shujaa", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ipswy/senti-shujaa with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ipswy/senti-shujaa

SGLang

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

Docker Model Runner
How to use ipswy/senti-shujaa with Docker Model Runner:
```
docker model run hf.co/ipswy/senti-shujaa
```

ipswy commited on Jun 10

Commit

06f3fdd

verified ·

1 Parent(s): 37906e6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +37 -63

README.md CHANGED Viewed

@@ -1,63 +1,37 @@
----
-base_model: unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
-library_name: peft
-model_name: senti_shujaa_v4
-tags:
-- base_model:adapter:unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
-- lora
-- sft
-- transformers
-- trl
-- unsloth
-licence: license
-pipeline_tag: text-generation
----
-# Model Card for senti_shujaa_v4
-This model is a fine-tuned version of [unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-## Training procedure
-This model was trained with SFT.
-### Framework versions
-- PEFT 0.18.1
-- TRL: 0.24.0
-- Transformers: 5.5.0
-- Pytorch: 2.10.0+cu128
-- Datasets: 4.3.0
-- Tokenizers: 0.22.2
-## Citations
-Cite TRL as:
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```

+---
+license: apache-2.0
+language:
+- en
+- sw
+tags:
+- finance
+- kenya
+- africa
+- qwen2
+- lora
+- senti-ai
+pipeline_tag: text-generation
+library_name: transformers
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+---
+# Senti-Shujaa V4
+**Senti-Shujaa** is a finance-specialized language model fine-tuned for Kenya and East Africa.
+## Model Details
+- **Base Model**: Qwen2.5-1.5B-Instruct
+- **Fine-tuning**: LoRA (rank=16, alpha=128) with DPO
+- **Training**: Unsloth + 4-bit QLoRA on finance-specific data
+- **Languages**: English, Swahili, Sheng
+## Capabilities
+- PAYE/Tax calculations routing
+- Budget planning and coaching
+- Credit scoring and risk assessment
+- SACCO portfolio analysis
+- Compliance and regulatory guidance (KRA, SASRA)
+- Swahili and Sheng financial literacy
+## Usage
+This model is served via the HuggingFace Serverless Inference API as the Brain of Senti AI.