Instructions to use Defetya/ru-llama2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Defetya/ru-llama2-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Defetya/ru-llama2-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Defetya/ru-llama2-7B") model = AutoModelForCausalLM.from_pretrained("Defetya/ru-llama2-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Defetya/ru-llama2-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Defetya/ru-llama2-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Defetya/ru-llama2-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Defetya/ru-llama2-7B
- SGLang
How to use Defetya/ru-llama2-7B 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 "Defetya/ru-llama2-7B" \ --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": "Defetya/ru-llama2-7B", "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 "Defetya/ru-llama2-7B" \ --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": "Defetya/ru-llama2-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Defetya/ru-llama2-7B with Docker Model Runner:
docker model run hf.co/Defetya/ru-llama2-7B
Download model-00002-of-00002.safetensors from Defetya/ru-llama2-7B: direct link, hf CLI and curl.
- Browser
- Download file 3.5 GB
-
https://huggingface.co/Defetya/ru-llama2-7B/resolve/refs%2Fpr%2F10/model-00002-of-00002.safetensors
- Command line
-
hf download hf://Defetya/ru-llama2-7B@refs/pr/10/model-00002-of-00002.safetensors
-
curl -L -o model-00002-of-00002.safetensors https://huggingface.co/Defetya/ru-llama2-7B/resolve/refs%2Fpr%2F10/model-00002-of-00002.safetensors
3.5 GB
- Xet hash:
- 16f84dba515e63385f84cc3f9111c76190faa819287151f81c02aeaad42250ae
- Size of remote file:
- 3.5 GB
- SHA256:
- f5c85c220e75b0ddf23ab6b9aae08b0865b7d9b3ece0a817c9ec442831d75c78
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.