Text Generation
Transformers
Safetensors
English
modernbert
fill-mask
sentiment-control
continuous-control
controllable-text-generation
encoder-generation
non-autoregressive
masked-language-model
text-style-transfer
data-augmentation
emnlp2026
Instructions to use shawhed/SenseShift-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shawhed/SenseShift-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shawhed/SenseShift-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("shawhed/SenseShift-base") model = AutoModelForMaskedLM.from_pretrained("shawhed/SenseShift-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use shawhed/SenseShift-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shawhed/SenseShift-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shawhed/SenseShift-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/shawhed/SenseShift-base
- SGLang
How to use shawhed/SenseShift-base 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 "shawhed/SenseShift-base" \ --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": "shawhed/SenseShift-base", "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 "shawhed/SenseShift-base" \ --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": "shawhed/SenseShift-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use shawhed/SenseShift-base with Docker Model Runner:
docker model run hf.co/shawhed/SenseShift-base
Fix cross-link to SenseShift-large
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ choose on a continuous scale from **−1.0 to +1.0**, in context.
|
|
| 27 |
| Model | Base | Params |
|
| 28 |
| --- | --- | --- |
|
| 29 |
| **SenseShift-base** (this model) | ModernBERT-base | 150M |
|
| 30 |
-
| [SenseShift-large](https://huggingface.co/shawhed/SenseShift-
|
| 31 |
|
| 32 |
Accepted to EMNLP 2026.
|
| 33 |
|
|
|
|
| 27 |
| Model | Base | Params |
|
| 28 |
| --- | --- | --- |
|
| 29 |
| **SenseShift-base** (this model) | ModernBERT-base | 150M |
|
| 30 |
+
| [SenseShift-large](https://huggingface.co/shawhed/SenseShift-large) | ModernBERT-large | 396M |
|
| 31 |
|
| 32 |
Accepted to EMNLP 2026.
|
| 33 |
|