Instructions to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct") model = PeftModel.from_pretrained(base_model, "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter") - Transformers
How to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter
- SGLang
How to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter 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 "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter" \ --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": "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter", "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 "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter" \ --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": "Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter with Docker Model Runner:
docker model run hf.co/Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter
Upload EINSOF-II DeepSeek-V4.1 Flash 16B MoE Stiefel Polar LoRA Adapter with order 4 Stiefel retraction (Exit Code 0)
fec0b49 verified |
Download README.md from Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter: direct link, hf CLI and curl.
- Browser
- Download file 1.63 kB
-
https://huggingface.co/Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter/resolve/main/README.md
- Command line
-
hf download hf://Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter/README.md
-
curl -L -o README.md https://huggingface.co/Polydim-Einsof/einsof2-deepseek-v4-stiefel-adapter/resolve/main/README.md
1.63 kB
| base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | |
| library_name: peft | |
| model_name: einsof2_deepseek_v4_stiefel_adapter | |
| tags: | |
| - base_model:adapter:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | |
| - lora | |
| - sft | |
| - transformers | |
| - trl | |
| licence: license | |
| pipeline_tag: text-generation | |
| # Model Card for einsof2_deepseek_v4_stiefel_adapter | |
| This model is a fine-tuned version of [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct). | |
| It has been trained using [TRL](https://github.com/huggingface/trl). | |
| ## Quick start | |
| ```python | |
| from transformers import pipeline | |
| question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" | |
| generator = pipeline("text-generation", model="None", device_map="auto") | |
| output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] | |
| print(output["generated_text"]) | |
| ``` | |
| ## Training procedure | |
| This model was trained with SFT. | |
| ### Framework versions | |
| - PEFT 0.21.2 | |
| - TRL: 1.18.0 | |
| - Transformers: 5.20.2 | |
| - Pytorch: 2.11.0+cu130 | |
| - Datasets: 4.8.5 | |
| - Tokenizers: 0.23.3 | |
| ## Citations | |
| Cite TRL as: | |
| ```bibtex | |
| @software{vonwerra2020trl, | |
| title = {{TRL: Transformers Reinforcement Learning}}, | |
| author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin and Dirhoussi, Amine}, | |
| license = {Apache-2.0}, | |
| url = {https://github.com/huggingface/trl}, | |
| year = {2020} | |
| } | |
| ``` |