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

Libraries

How to use Captainsl/SinhalaLLM with Transformers:

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

pipe = pipeline("text-generation", model="Captainsl/SinhalaLLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Captainsl/SinhalaLLM")
model = AutoModelForCausalLM.from_pretrained("Captainsl/SinhalaLLM")

llama-cpp-python

How to use Captainsl/SinhalaLLM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Captainsl/SinhalaLLM",
	filename="SinhalaLLM.f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Captainsl/SinhalaLLM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Captainsl/SinhalaLLM:F16
# Run inference directly in the terminal:
llama-cli -hf Captainsl/SinhalaLLM:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Captainsl/SinhalaLLM:F16
# Run inference directly in the terminal:
llama-cli -hf Captainsl/SinhalaLLM:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Captainsl/SinhalaLLM:F16
# Run inference directly in the terminal:
./llama-cli -hf Captainsl/SinhalaLLM:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Captainsl/SinhalaLLM:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Captainsl/SinhalaLLM:F16

Use Docker

docker model run hf.co/Captainsl/SinhalaLLM:F16

LM Studio
Jan

vLLM

How to use Captainsl/SinhalaLLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Captainsl/SinhalaLLM:F16

SGLang

How to use Captainsl/SinhalaLLM 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 "Captainsl/SinhalaLLM" \
    --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": "Captainsl/SinhalaLLM",
		"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 "Captainsl/SinhalaLLM" \
        --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": "Captainsl/SinhalaLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Captainsl/SinhalaLLM with Ollama:
```
ollama run hf.co/Captainsl/SinhalaLLM:F16
```

Unsloth Studio new

How to use Captainsl/SinhalaLLM 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 Captainsl/SinhalaLLM 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 Captainsl/SinhalaLLM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Captainsl/SinhalaLLM to start chatting

Docker Model Runner
How to use Captainsl/SinhalaLLM with Docker Model Runner:
```
docker model run hf.co/Captainsl/SinhalaLLM:F16
```

Lemonade

How to use Captainsl/SinhalaLLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Captainsl/SinhalaLLM:F16

Run and chat with the model

lemonade run user.SinhalaLLM-F16

List all available models

lemonade list

Sinhala Language Model Research - SmolLM2 Fine-tuning Attempt

⚠️ EXPERIMENTAL MODEL - NOT FOR PRODUCTION USE

Model Description

Base Model: HuggingFaceTB/SmolLM2-1.7B
Fine-tuning Method: QLoRA (4-bit quantization with LoRA)
Target Language: Sinhala (සිංහල)
Status: Research prototype with significant limitations

Research Context

This model represents an undergraduate research attempt to adapt SmolLM2-1.7B for Sinhala language generation. Part of thesis: "Developing a Fluent Sinhala Language Model: Enhancing AI's Cultural and Linguistic Adaptability" (NSBM Green University, 2025).

Training Details

Dataset

Size: 427,000 raw examples → 406,532 after cleaning
Sources:
- YouTube comments (32%)
- Web scraped content (35%)
- Translated instructions (23%)
- Curated texts (10%)
Data Quality: Mixed (social media, news, translated content)
Processing: Custom cleaning pipeline removing URLs, emails, duplicates

Training Configuration

Hardware: NVIDIA RTX 4090 (24GB VRAM) via Vast.ai
Training Time: 48 hours
Total Cost: $19.20 (budget-constrained research)
Framework: Unsloth for memory efficiency
LoRA Parameters:
- Rank (r): 16
- Alpha: 16
- Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- Trainable parameters: 8.4M/1.7B (99.5% reduction)

Hyperparameters

Learning rate: 2e-5
Batch size: 8 (gradient accumulation: 1)
Max sequence length: 2048 (reduced to 512 for memory)
Mixed precision: FP16
Optimizer: adamw_8bit

Evaluation Results

Quantitative Metrics

Perplexity: 218,443 (target was <50) ❌
BLEU Score: 0.0000 ❌
Training Loss: 1.847 (converged)
Task Completion Rate:
- General conversation: 0%
- Mathematics: 100% (but output corrupted)
- Cultural context: 0%
- Instruction following: 33%

Critical Issues Discovered

⚠️ Tokenizer Incompatibility: The model exhibits catastrophic tokenizer-model mismatch, generating English vocabulary tokens ("Drum", "Chiefs", "RESP") instead of Sinhala text. This represents a fundamental architectural incompatibility between SmolLM2's tokenizer and Sinhala script.

Sample Outputs (Showing Failure Pattern)

Input: "ඔබේ නම කුමක්ද?"
Expected: "මගේ නම [name] වේ"
Actual: "Drum Chiefs RESP frontend(direction..."

Research Contributions

Despite technical failure, this research provides:

Dataset: 427,000 curated Sinhala examples (largest publicly available)
Pipeline: Reproducible training framework for low-resource languages
Discovery: Documentation of critical tokenizer challenges for non-Latin scripts
Methodology: Budget-conscious approach ($30 total) for LLM research

Limitations & Warnings

❌ Does NOT generate coherent Sinhala text
❌ Tokenizer fundamentally incompatible with Sinhala
❌ Not suitable for any production use
✅ Useful only as research artifact and negative result documentation

Intended Use

This model is shared for:

Academic transparency and reproducibility
Documentation of challenges in low-resource language AI
Foundation for future research improvements
Example of tokenizer-model compatibility issues

Recommendations for Future Work

Use multilingual base models (mT5, XLM-R, BLOOM)
Develop Sinhala-specific tokenizer
Increase dataset to 1M+ examples
Consider character-level or byte-level models

How to Reproduce Issues

# This will demonstrate the tokenizer problem
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("path/to/model")
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B")

input_text = "ශ්‍රී ලංකාව"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)
print(tokenizer.decode(outputs[0]))
# Output will be gibberish English tokens

Citation

@thesis{dharmasiri2025sinhala,
  title={Developing a Fluent Sinhala Language Model: Enhancing AI's Cultural and Linguistic Adaptability},
  author={Dharmasiri, H.M.A.H.},
  year={2025},
  school={NSBM Green University},
  note={Undergraduate thesis documenting challenges in low-resource language AI}
}

Ethical Considerations

Model outputs are not reliable for Sinhala generation
Should not be used for any decision-making
Shared for research transparency only

License

MIT License - for research and educational purposes

Downloads last month: 19

Safetensors

Model size

2B params

Tensor type

F16

Model tree for Captainsl/SinhalaLLM

Base model

HuggingFaceTB/SmolLM2-1.7B

Quantized

(38)

this model

Quantizations

1 model