Instructions to use ecloudtech/Erk-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ecloudtech/Erk-14B with Transformers:

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

pipe = pipeline("text-generation", model="ecloudtech/Erk-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ecloudtech/Erk-14B")
model = AutoModelForCausalLM.from_pretrained("ecloudtech/Erk-14B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ecloudtech/Erk-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ecloudtech/Erk-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ecloudtech/Erk-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ecloudtech/Erk-14B

SGLang

How to use ecloudtech/Erk-14B 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 "ecloudtech/Erk-14B" \
    --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": "ecloudtech/Erk-14B",
		"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 "ecloudtech/Erk-14B" \
        --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": "ecloudtech/Erk-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ecloudtech/Erk-14B with Docker Model Runner:
```
docker model run hf.co/ecloudtech/Erk-14B
```

Erk-14B

Commit History

Oct 2

05:18
Recete: tohum 2 sonucu

aigencydev

Verified signature
8584b14

Oct 1

18:01
Recete: asama tablosu, ablasyon, tohum, TurBLiMP

aigencydev

Verified signature
6ad00ff
04:57
Kart: tam kume TurkishMMLU (v1/v2) ve bagimsiz TurBLiMP sonucu

aigencydev

Verified signature
0f52dc5

Sep 30

17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
b31cbb1
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
352e6ad
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
14ac35b
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
a695171
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
7748901
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
0b8f695
17:57
egitim/: v2 betikleri ve veri ozetleri

aigencydev

Verified signature
941efec
17:56
Egitim recetesi v2

aigencydev

Verified signature
c52d8d6
17:56
Kart: v1/v2 olcumleri ayrildi, lisans ifadesi, egitim recetesi baglantisi

aigencydev

Verified signature
6772cc4

Sep 29

14:40
Erk-14B v2 (main): agirliklar + sablon

aigencydev

Verified signature
7e63823
14:37
Surum 2 karti (main)

aigencydev

Verified signature
88a7d58

Sep 21

09:29
Standart Qwen3 mimarisine geciliyor: model her arac tarafindan yuklenebilir⁠

aigencydev

Verified signature
e14df4c
09:25
Kart: savunulamaz siralama iddialari kaldirildi⁠

aigencydev

Verified signature
e4cd16d

Sep 8

06:21
TurkishMMLU: kirlilik disi, sik dondurmeli protokolde ek olcum (%67,18); ayrinti Erk-32B raporunda

aigencydev

Verified signature
3be9b60

Jul 29

11:54
Update README.md

aigencydev

Verified signature
2ab0b27

Jul 21

11:12
Seffaflik: temel modeli (Qwen3-14B) acikca belirt; sifirdan/tokenizer iddialarini duzelt

aigencydev

Verified signature
576e3c8

Jul 20

15:05
Lisans linkini tam URL yap (goreli link HF tree/ olarak cozulup 404 veriyordu)

aigencydev

Verified signature
037ebbb
10:14
Upload README.md with huggingface_hub

aigencydev

Verified signature
bfd8a1a

Jul 19

18:32
Upload README.md with huggingface_hub

aigencydev

Verified signature
ee90d96
18:06
Upload README.md with huggingface_hub

aigencydev

Verified signature
c28e1ba
17:55
Upload folder using huggingface_hub

aigencydev

Verified signature
b648ce9
17:47
initial commit

aigencydev

Verified signature
ff129f2

Commit History

Oct 2

Recete: tohum 2 sonucu

Oct 1

Recete: asama tablosu, ablasyon, tohum, TurBLiMP

Kart: tam kume TurkishMMLU (v1/v2) ve bagimsiz TurBLiMP sonucu

Sep 30

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

egitim/: v2 betikleri ve veri ozetleri

Egitim recetesi v2

Kart: v1/v2 olcumleri ayrildi, lisans ifadesi, egitim recetesi baglantisi

Sep 29

Erk-14B v2 (main): agirliklar + sablon

Surum 2 karti (main)

Sep 21

Standart Qwen3 mimarisine geciliyor: model her arac tarafindan yuklenebilir⁠

Kart: savunulamaz siralama iddialari kaldirildi⁠

Sep 8

TurkishMMLU: kirlilik disi, sik dondurmeli protokolde ek olcum (%67,18); ayrinti Erk-32B raporunda

Jul 29

Update README.md

Jul 21

Seffaflik: temel modeli (Qwen3-14B) acikca belirt; sifirdan/tokenizer iddialarini duzelt

Jul 20

Lisans linkini tam URL yap (goreli link HF tree/ olarak cozulup 404 veriyordu)

Upload README.md with huggingface_hub

Jul 19

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload folder using huggingface_hub

initial commit