Instructions to use Mykes/medicus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Mykes/medicus with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mykes/medicus:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mykes/medicus:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mykes/medicus:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mykes/medicus:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Mykes/medicus:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Mykes/medicus:Q4_K_M
Use Docker
docker model run hf.co/Mykes/medicus:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Mykes/medicus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mykes/medicus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Mykes/medicus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Mykes/medicus:Q4_K_M
- Ollama
How to use Mykes/medicus with Ollama:
ollama run hf.co/Mykes/medicus:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Mykes/medicus with Docker Model Runner:
docker model run hf.co/Mykes/medicus:Q4_K_M
- Lemonade
How to use Mykes/medicus with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mykes/medicus:Q4_K_M
Run and chat with the model
lemonade run user.medicus-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ The fine-tuning process utilized the [Continued Pretraining](https://docs.unslot
|
|
| 31 |
- **Training Method**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 32 |
- **Epochs**: 10
|
| 33 |
- **Resources**: 1 RTX A5000 24Gb vRAM for approximately 3 days. The cost of finetuning is about $54.
|
| 34 |
-
**License:** This model is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 35 |
### Quantization Options
|
| 36 |
|
| 37 |
Medicus supports multiple quantization levels to allow flexible deployment based on computational resources:
|
|
@@ -198,7 +198,7 @@ For issues, questions, or suggestions, feel free to open an issue in the reposit
|
|
| 198 |
- **Метод обучения**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 199 |
- **Количество эпох**: 10
|
| 200 |
- **Оборужование**: 1 RTX A5000 24Gb vRAM приблизительно в течение 3-х дней. Общие затраты на файнтюнинг около $54.
|
| 201 |
-
**Лицензия:** Модель распространяетчя по лицензии Google [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 202 |
### Варианты квантизации
|
| 203 |
|
| 204 |
Medicus поддерживает различные уровни квантизации, что позволяет гибко развертывать модель в зависимости от доступных вычислительных ресурсов:
|
|
|
|
| 31 |
- **Training Method**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 32 |
- **Epochs**: 10
|
| 33 |
- **Resources**: 1 RTX A5000 24Gb vRAM for approximately 3 days. The cost of finetuning is about $54.
|
| 34 |
+
- **License:** This model is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 35 |
### Quantization Options
|
| 36 |
|
| 37 |
Medicus supports multiple quantization levels to allow flexible deployment based on computational resources:
|
|
|
|
| 198 |
- **Метод обучения**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 199 |
- **Количество эпох**: 10
|
| 200 |
- **Оборужование**: 1 RTX A5000 24Gb vRAM приблизительно в течение 3-х дней. Общие затраты на файнтюнинг около $54.
|
| 201 |
+
- **Лицензия:** Модель распространяетчя по лицензии Google [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 202 |
### Варианты квантизации
|
| 203 |
|
| 204 |
Medicus поддерживает различные уровни квантизации, что позволяет гибко развертывать модель в зависимости от доступных вычислительных ресурсов:
|