Instructions to use muzaffercky/Sorjin1-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use muzaffercky/Sorjin1-LoRA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B")
model = PeftModel.from_pretrained(base_model, "muzaffercky/Sorjin1-LoRA")

Transformers

How to use muzaffercky/Sorjin1-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="muzaffercky/Sorjin1-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("muzaffercky/Sorjin1-LoRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use muzaffercky/Sorjin1-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "muzaffercky/Sorjin1-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "muzaffercky/Sorjin1-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/muzaffercky/Sorjin1-LoRA

SGLang

How to use muzaffercky/Sorjin1-LoRA 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 "muzaffercky/Sorjin1-LoRA" \
    --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": "muzaffercky/Sorjin1-LoRA",
		"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 "muzaffercky/Sorjin1-LoRA" \
        --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": "muzaffercky/Sorjin1-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use muzaffercky/Sorjin1-LoRA with Docker Model Runner:
```
docker model run hf.co/muzaffercky/Sorjin1-LoRA
```

Sorjîn1-LoRA

The raw LoRA adapter weights from continual pretraining of Qwen/Qwen2.5-7B on Kurdish Kurmanji academic theses.

Use this if you want to apply the Kurdish language adapter to a different Qwen2.5-7B variant, or retrain from this checkpoint.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B", torch_dtype="bfloat16")
model = PeftModel.from_pretrained(base, "muzaffercky/Sorjin1-LoRA")

# Merge adapter into base weights
model = model.merge_and_unload()

Training Details

Base model: Qwen/Qwen2.5-7B
Dataset: muzaffercky/kurdish-kurmanji-theses
LoRA rank: 64 | Alpha: 128 | Dropout: 0.05
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Trainable parameters: 161,480,704 (2.08% of total)
Final train loss: 2.057 | Final eval loss: 1.8552

Model Family

Model	Description
Sorjîn1-LoRA (this model)	Raw LoRA adapter weights
Sorjîn1-7B	Continually pretrained base model
Sorjîn1-7B-Instruct	Merged with Qwen2.5-7B-Instruct

Downloads last month: 30

Model tree for muzaffercky/Sorjin1-LoRA

Base model

Qwen/Qwen2.5-7B

Adapter

(554)

this model

Dataset used to train muzaffercky/Sorjin1-LoRA

Collection including muzaffercky/Sorjin1-LoRA

Sorjîn1

Collection

3 items • Updated Jun 6