Text Generation
Transformers
Safetensors
English
psychometrics
personality
mental-health
computational-psychology
adapter-tuning
Instructions to use huvucode/PsychAdapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huvucode/PsychAdapter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huvucode/PsychAdapter")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("huvucode/PsychAdapter", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huvucode/PsychAdapter with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huvucode/PsychAdapter" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huvucode/PsychAdapter", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huvucode/PsychAdapter
- SGLang
How to use huvucode/PsychAdapter 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 "huvucode/PsychAdapter" \ --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": "huvucode/PsychAdapter", "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 "huvucode/PsychAdapter" \ --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": "huvucode/PsychAdapter", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huvucode/PsychAdapter with Docker Model Runner:
docker model run hf.co/huvucode/PsychAdapter
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,11 +40,7 @@ The model checkpoints are provided as separate ZIP files to keep the psychologic
|
|
| 40 |
* **decoder**: Contains the shared base model/decoder weights required by all adapters.
|
| 41 |
|
| 42 |
### 2. Assembly Instructions:
|
| 43 |
-
All model directories contain an empty `decoder/` subdirectory. To use the models, you must manually populate
|
| 44 |
-
|
| 45 |
-
1. Unzip your desired model (e.g., `big5_model.zip`).
|
| 46 |
-
2. Unzip `decoder.zip`.
|
| 47 |
-
3. Copy the entire **content** of the unzipped `decoder` folder into the `decoder/` directory located inside your model folder (e.g., `big5_model/decoder/`).
|
| 48 |
|
| 49 |
**Note:** The models will fail to load if the `decoder/` directory is empty or missing the shared weights.
|
| 50 |
|
|
|
|
| 40 |
* **decoder**: Contains the shared base model/decoder weights required by all adapters.
|
| 41 |
|
| 42 |
### 2. Assembly Instructions:
|
| 43 |
+
All model directories contain an empty `decoder/` subdirectory. To use the models, you must manually populate this directory by copying the entire **content** of the `decoder` folder into the `decoder/` directory located inside your model folder (e.g., `big5_model/decoder/`).
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
**Note:** The models will fail to load if the `decoder/` directory is empty or missing the shared weights.
|
| 46 |
|