Text Generation
Transformers
Safetensors
Russian
English
aurora2
mixture-of-experts
russian
continued-pretraining
custom_code
Instructions to use AdminHugging/aurora2-ru-400m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdminHugging/aurora2-ru-400m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdminHugging/aurora2-ru-400m", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AdminHugging/aurora2-ru-400m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdminHugging/aurora2-ru-400m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdminHugging/aurora2-ru-400m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/aurora2-ru-400m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdminHugging/aurora2-ru-400m
- SGLang
How to use AdminHugging/aurora2-ru-400m 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 "AdminHugging/aurora2-ru-400m" \ --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": "AdminHugging/aurora2-ru-400m", "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 "AdminHugging/aurora2-ru-400m" \ --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": "AdminHugging/aurora2-ru-400m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdminHugging/aurora2-ru-400m with Docker Model Runner:
docker model run hf.co/AdminHugging/aurora2-ru-400m
Commit History
Yesterday
-
card: v2 (150M токенов, en в миксе, C#/Rust)
Verified signature4cd4dbb -
remove stale v1 ckpt/weights_bf16.pt
Verified signature199e914 -
remove stale v1 ckpt/last.pt
Verified signature2674915 -
remove stale v1 ckpt/config.json
Verified signature856b10d -
update: v2 (150M токенов, английский в миксе, C#/Rust)
Verified signaturecae3348 -
remove link to private kaggle kernel
Verified signature16ce497 -
fix: unambiguous wording for the 32% token row + example
Verified signature2a53fd8 -
model card: токенизатор, метрики, бенчмарки, ограничения
Verified signature4a336f1 -
Upload folder using huggingface_hub
Verified signaturef21dc1b -
Upload ckpt/last.pt with huggingface_hub
Verified signaturecfb63fe -
Upload logs/metrics.csv with huggingface_hub
Verified signatureedf357e -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signaturef32c24c -
Upload logs/metrics.csv with huggingface_hub
Verified signature5dffef4 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signaturef5a395f -
Upload logs/metrics.csv with huggingface_hub
Verified signaturea3a80c5 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signaturea492247 -
Upload logs/metrics.csv with huggingface_hub
Verified signature453977e -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signature7fc1c32
2 days ago
-
Upload logs/metrics.csv with huggingface_hub
Verified signaturee3053cb -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signature5c010d1 -
Upload logs/metrics.csv with huggingface_hub
Verified signaturef152b40 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signature5eada8b -
Upload logs/metrics.csv with huggingface_hub
Verified signature2f78b87 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signature82d661b -
Upload logs/metrics.csv with huggingface_hub
Verified signature12451d6 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signaturedd47742 -
Upload logs/metrics.csv with huggingface_hub
Verified signature5d5d0ae -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signatureb272aba -
Upload model/ext/config.json with huggingface_hub
Verified signature5595946 -
Upload model/ext/tokenizer_config.json with huggingface_hub
Verified signature8cf1134 -
Upload model/ext/tokenizer.json with huggingface_hub
Verified signature6080beb -
Upload model/ext/extend_meta.json with huggingface_hub
Verified signature0832ab3 -
Upload logs/config_used.yaml with huggingface_hub
Verified signature9bd8b33 -
Upload logs/metrics.csv with huggingface_hub
Verified signatureefc92a6 -
Upload ckpt/config.json with huggingface_hub
Verified signature98ddae8 -
Upload ckpt/weights_bf16.pt with huggingface_hub
Verified signature2109d78 -
initial commit
Verified signature21faf67