Instructions to use AhiskaAI/AhiskaAI-65m-Base-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AhiskaAI/AhiskaAI-65m-Base-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="AhiskaAI/AhiskaAI-65m-Base-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AhiskaAI/AhiskaAI-65m-Base-v0.2")
model = AutoModelForCausalLM.from_pretrained("AhiskaAI/AhiskaAI-65m-Base-v0.2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AhiskaAI/AhiskaAI-65m-Base-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AhiskaAI/AhiskaAI-65m-Base-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AhiskaAI/AhiskaAI-65m-Base-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AhiskaAI/AhiskaAI-65m-Base-v0.2

SGLang

How to use AhiskaAI/AhiskaAI-65m-Base-v0.2 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 "AhiskaAI/AhiskaAI-65m-Base-v0.2" \
    --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": "AhiskaAI/AhiskaAI-65m-Base-v0.2",
		"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 "AhiskaAI/AhiskaAI-65m-Base-v0.2" \
        --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": "AhiskaAI/AhiskaAI-65m-Base-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AhiskaAI/AhiskaAI-65m-Base-v0.2 with Docker Model Runner:
```
docker model run hf.co/AhiskaAI/AhiskaAI-65m-Base-v0.2
```

AhiskaAI-65m-Base-v0.2 / README.md

YunusEmreSaidoglu

Update README.md

2b11ddb verified 13 days ago

preview code

Raw

History Blame Contribute Delete

3.01 kB

	---
	license: apache-2.0
	language:
	- tr
	pipeline_tag: text-generation
	tags:
	- slm
	- base-model
	- causal-lm
	- pre-trained
	- tr-llm
	- Ahıska
	- AhiskaTurks
	- MeskhetianTurks
	- AhıskaTürkleri
	library_name: transformers

	---

	# AhiskaAI-65m-Base-v0.2

	AhiskaAI-65m-Base-v0.2 is a 65 million parameter Small Language Model (SLM) built from scratch. It is the lightweight member of the AhiskaAI v0.2 family, designed to provide efficient Turkish language understanding on resource-constrained hardware.

	## Model Details

	- Architecture: Llama-based architecture.
	- Parameters: 65M.
	- Context Window: 1024 tokens.
	- Tokenizer: Custom BPE Tokenizer (Vocabulary Size: 32,000).
	- Training Framework: PyTorch & Transformers.

	---

	## Data Curation (The "Quality over Quantity" Approach)

	A major improvement in the v0.2 release is the adoption of a data-centric training pipeline.

	- Raw Data (v0.1): 5GB of raw Turkish corpus.
	- Curated Data (v0.2): 1.2GB of carefully filtered, high-quality Turkish text.
	- Process: Approximately 75% of noisy, duplicated, and low-quality samples were removed to maximize linguistic quality and training efficiency.

	---

	## Key Improvements from v0.1

	- Architecture Shift: Migrated from GPT-2 to a modern Llama-based architecture.
	- Normalization: RMSNorm.
	- Positional Encoding: RoPE (Rotary Positional Embeddings).
	- Activation: SiLU.
	- Precision: Trained using bfloat16 for efficient consumer GPU training.

	---

	## Design Goal

	Unlike larger language models, the 65M variant focuses on efficiency while preserving core language understanding abilities.

	The objective of this model is not to maximize factual knowledge, but to provide:

	- Strong Turkish language modeling.
	- Basic instruction understanding.
	- Fast inference on low-resource hardware.
	- A compact research baseline for future AhiskaAI releases.

	---

	## Training Logs
	![Training Loss Curve](training_loss.png)
	The graph above demonstrates the training convergence of AhiskaAI-65m-Base-v0.2. The stable decline in loss confirms the effective alignment of the model architecture with the curated Turkish dataset.

	---

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained("AhiskaAI/AhiskaAI-65m-Base-v0.2")
	tokenizer = AutoTokenizer.from_pretrained("AhiskaAI/AhiskaAI-65m-Base-v0.2")

	text = "Türkiye Cumhuriyeti"
	inputs = tokenizer(text, return_tensors="pt")

	outputs = model.generate(**inputs, max_new_tokens=50)

	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	---

	## Training Hardware

	Trained on NVIDIA RTX 4050 6GB Laptop GPU.

	---

	## Future Plans

	- Larger context windows.
	- Improved Turkish datasets.
	- Future v0.3 model family.
	---

	## About AhiskaAI

	AhiskaAI is an independent open-source initiative dedicated to developing efficient Turkish Small Language Models trained completely from scratch.
	Follow us on Hugging Face for updates and new releases.