Text Generation
Transformers
Safetensors
Turkish
ozan_llm
feature-extraction
turkish
turkce
causal-lm
ozanllm
base-model
pretraining
custom_code
Instructions to use coderian/OzanLLM-40M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use coderian/OzanLLM-40M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="coderian/OzanLLM-40M", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("coderian/OzanLLM-40M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use coderian/OzanLLM-40M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "coderian/OzanLLM-40M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "coderian/OzanLLM-40M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/coderian/OzanLLM-40M
- SGLang
How to use coderian/OzanLLM-40M 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 "coderian/OzanLLM-40M" \ --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": "coderian/OzanLLM-40M", "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 "coderian/OzanLLM-40M" \ --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": "coderian/OzanLLM-40M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use coderian/OzanLLM-40M with Docker Model Runner:
docker model run hf.co/coderian/OzanLLM-40M
Download config.json from coderian/OzanLLM-40M: direct link, hf CLI and curl.
- Browser
- Download file 408 Bytes
-
https://huggingface.co/coderian/OzanLLM-40M/resolve/main/config.json
- Command line
-
hf download hf://coderian/OzanLLM-40M/config.json
-
curl -L -o config.json https://huggingface.co/coderian/OzanLLM-40M/resolve/main/config.json
408 Bytes
| { | |
| "architectures": [ | |
| "OzanForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_ozanllm.GPTConfig", | |
| "AutoModel": "model.OzanForCausalLM", | |
| "AutoModelForCausalLM": "model.OzanForCausalLM" | |
| }, | |
| "dtype": "float32", | |
| "embed_dim": 320, | |
| "max_seq_len": 512, | |
| "model_type": "ozan_llm", | |
| "n_layers": 5, | |
| "transformers_version": "5.0.0", | |
| "use_cache": false, | |
| "vocab_size": 50000 | |
| } | |