Instructions to use klei1/bleta-meditor-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use klei1/bleta-meditor-27b with Transformers:

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

pipe = pipeline("text-generation", model="klei1/bleta-meditor-27b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("klei1/bleta-meditor-27b")
model = AutoModelForCausalLM.from_pretrained("klei1/bleta-meditor-27b")
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]:]))

llama-cpp-python

How to use klei1/bleta-meditor-27b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="klei1/bleta-meditor-27b",
	filename="bleta-meditor-27b-finetune.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use klei1/bleta-meditor-27b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf klei1/bleta-meditor-27b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf klei1/bleta-meditor-27b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf klei1/bleta-meditor-27b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf klei1/bleta-meditor-27b:Q8_0

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 klei1/bleta-meditor-27b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf klei1/bleta-meditor-27b:Q8_0

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 klei1/bleta-meditor-27b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf klei1/bleta-meditor-27b:Q8_0

Use Docker

docker model run hf.co/klei1/bleta-meditor-27b:Q8_0

LM Studio
Jan

vLLM

How to use klei1/bleta-meditor-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "klei1/bleta-meditor-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "klei1/bleta-meditor-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/klei1/bleta-meditor-27b:Q8_0

SGLang

How to use klei1/bleta-meditor-27b 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 "klei1/bleta-meditor-27b" \
    --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": "klei1/bleta-meditor-27b",
		"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 "klei1/bleta-meditor-27b" \
        --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": "klei1/bleta-meditor-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use klei1/bleta-meditor-27b with Ollama:
```
ollama run hf.co/klei1/bleta-meditor-27b:Q8_0
```

Unsloth Studio new

How to use klei1/bleta-meditor-27b 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 klei1/bleta-meditor-27b 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 klei1/bleta-meditor-27b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for klei1/bleta-meditor-27b to start chatting

Docker Model Runner
How to use klei1/bleta-meditor-27b with Docker Model Runner:
```
docker model run hf.co/klei1/bleta-meditor-27b:Q8_0
```

Lemonade

How to use klei1/bleta-meditor-27b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull klei1/bleta-meditor-27b:Q8_0

Run and chat with the model

lemonade run user.bleta-meditor-27b-Q8_0

List all available models

lemonade list

Bleta-Meditor 27B GRPO Albanian Reasoning Model

Model Description

Developed by: klei aliaj
Model type: Bleta-Meditor 27B fine-tuned with GRPO for Albanian reasoning tasks
License: apache-2.0
Finetuned from model: Bleta-Meditor 27B (based on Gemma 3 architecture)
Language: Albanian
Framework: Hugging Face Transformers

This model is a fine-tuned version of the Bleta-Meditor 27B model, specifically optimized for the Albanian language using Generative Rejection Policy Optimization (GRPO) to improve its reasoning capabilities. Bleta is an Albanian adaptation based on Google's Gemma 3 architecture.

Capabilities & Training

Fine-tuning Approach

This Albanian language model was fine-tuned using GRPO (Generative Rejection Policy Optimization), a reinforcement learning technique that trains models to optimize for specific reward functions. The model was trained to:

Follow a specific reasoning format with dedicated sections for workings and solutions
Produce correct mathematical solutions in Albanian
Show clear step-by-step reasoning processes

Special Formatting

The model has been trained to follow a specific reasoning format:

Working out/reasoning sections are enclosed within <start_working_out> and <end_working_out> tags
Final solutions are provided between <SOLUTION> and </SOLUTION> tags

Training Configuration

Framework: Hugging Face's TRL library
Optimization: LoRA fine-tuning (r=8, alpha=8)
Reward Functions: Format adherence, answer accuracy, and reasoning quality
Language Focus: Optimized for Albanian

Technical Specifications

Available Formats

This model is available in two formats:

Standard adapter format (adapter_model.safetensors)
GGUF 8-bit quantized format (bleta-meditor-27b-finetune.Q8_0.gguf) for use with llama.cpp

Bleta-Meditor Architecture Benefits

27B parameters
128K context window
QK normalization
5 sliding + 1 global attention pattern
1024 sliding window attention
Albanian language optimization

Limitations

While this model excels at Albanian reasoning tasks, particularly mathematical problems, it may still occasionally provide incorrect solutions for complex problems.
The model's performance might vary depending on problem complexity and wording.
Like all language models, it may occasionally hallucinate or provide incorrect information outside its training domain.

Acknowledgments

Google for developing the Gemma 3 architecture
Hugging Face for their TRL library and GRPO implementation

Citation

If you use this model in your research, please cite:

@misc{klei_aliaj_bleta_meditor,
  author = {Klei Aliaj},
  title = {Bleta-Meditor 27B GRPO Albanian Reasoning Model},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/klei1/bleta-meditor-27b-finetune}}
}

Downloads last month: 29

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

8-bit

Collection including klei1/bleta-meditor-27b

Bleta 🐝

Collection

The Bleta Collection represents the continuous evolution of Albania’s digital services, offering innovative solutions tailored to the needs of citizen • 7 items • Updated Apr 21 • 3