Instructions to use Elfrino/PsyMedRose-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Elfrino/PsyMedRose-20B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Elfrino/PsyMedRose-20B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Elfrino/PsyMedRose-20B") model = AutoModelForCausalLM.from_pretrained("Elfrino/PsyMedRose-20B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Elfrino/PsyMedRose-20B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Elfrino/PsyMedRose-20B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Elfrino/PsyMedRose-20B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Elfrino/PsyMedRose-20B
- SGLang
How to use Elfrino/PsyMedRose-20B 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 "Elfrino/PsyMedRose-20B" \ --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": "Elfrino/PsyMedRose-20B", "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 "Elfrino/PsyMedRose-20B" \ --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": "Elfrino/PsyMedRose-20B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Elfrino/PsyMedRose-20B with Docker Model Runner:
docker model run hf.co/Elfrino/PsyMedRose-20B
| slices: | |
| - sources: | |
| - model: Undi95/PsyMedRP-v1-20B | |
| layer_range: [0, 62] # PsyMedRP has 62 layers | |
| - model: tavtav/Rose-20B | |
| layer_range: [0, 62] # MXLewd has 62 layers | |
| merge_method: slerp # Or use another method like weight_average if needed | |
| base_model: Undi95/PsyMedRP-v1-20B # PsyMedRP as the base for reasoning dominance | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0.3, 0.7, 1, 0.7, 0.4] # Boost creativity in pattern recognition | |
| - filter: mlp | |
| value: [0.2, 0.6, 1, 0.8, 0.5] # Emphasize creativity in decision-making and connections | |
| - value: 0.639 # Slight leaning toward PsyMedRP's base characteristics | |
| dtype: bfloat16 |