Text Generation
Transformers
Safetensors
llama
trl
kto
Generated from Trainer
text-generation-inference
Instructions to use stojchet/nkto1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stojchet/nkto1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="stojchet/nkto1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("stojchet/nkto1") model = AutoModelForCausalLM.from_pretrained("stojchet/nkto1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use stojchet/nkto1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "stojchet/nkto1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "stojchet/nkto1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/stojchet/nkto1
- SGLang
How to use stojchet/nkto1 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 "stojchet/nkto1" \ --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": "stojchet/nkto1", "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 "stojchet/nkto1" \ --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": "stojchet/nkto1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use stojchet/nkto1 with Docker Model Runner:
docker model run hf.co/stojchet/nkto1
Download params.json from stojchet/nkto1: direct link, hf CLI and curl.
- Browser
- Download file 393 Bytes
-
https://huggingface.co/stojchet/nkto1/resolve/main/params.json
- Command line
-
hf download hf://stojchet/nkto1/params.json
-
curl -L -o params.json https://huggingface.co/stojchet/nkto1/resolve/main/params.json
393 Bytes
| {"max_seq_length": 1000, "language": "python", "dataset_size": 14000, "epochs": 3, "per_device_train_batch_size": 8, "gradient_accumulation_steps": 16, "learning_rate": 1e-05, "no_lora": true, "lora_r": 64, "lora_alpha": 16, "lora_dropout": 0.05, "warmup_ratio": 0.1, "weight_decay": 0.1, "dataset_name": "stojchet/kto-final_base_dataset", "base_model": "deepseek-ai/deepseek-coder-1.3b-base"} |