Instructions to use Phora68/rapha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Phora68/rapha 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 Phora68/rapha:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Phora68/rapha:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Phora68/rapha:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Phora68/rapha:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Phora68/rapha:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Phora68/rapha:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Phora68/rapha:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Phora68/rapha:Q4_K_M

Use Docker

docker model run hf.co/Phora68/rapha:Q4_K_M

LM Studio
Jan
Ollama
How to use Phora68/rapha with Ollama:
```
ollama run hf.co/Phora68/rapha:Q4_K_M
```

Unsloth Studio

How to use Phora68/rapha with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Phora68/rapha to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Phora68/rapha to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Phora68/rapha to start chatting

Docker Model Runner
How to use Phora68/rapha with Docker Model Runner:
```
docker model run hf.co/Phora68/rapha:Q4_K_M
```

Lemonade

How to use Phora68/rapha with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Phora68/rapha:Q4_K_M

Run and chat with the model

lemonade run user.rapha-Q4_K_M

List all available models

lemonade list

Atomic Chat

Phora68 commited on 13 days ago

Commit

b44b670

verified ·

1 Parent(s): 01be0fe

Update model card

Browse files

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -2,15 +2,15 @@
 license: other
 base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
 tags:
-- clinical
-- medical
-- healthcare
-- qlora
-- unsloth
-- chatml
-- rapha
 language:
-- en
 ---
 # Rapha — Clinical AI Physician Assistant
@@ -24,7 +24,7 @@ never diagnoses.**
 - **Method:** QLoRA (Unsloth) → curriculum SFT → DPO
 - **Chat template:** ChatML
 - **Context window:** 8,192 tokens (training) / 4,096 (Ollama default)
-- **Trained:** 2026-07-31
 ## Training architecture (v2.6)
@@ -62,13 +62,13 @@ de-duplicated, leak-safe train/val split.
 | Metric | Value |
 |---|---|
-| empathy_rate | 0.4500 |
-| escalation_accuracy | 0.4444 |
-| adversarial_hold_rate | 0.6667 |
 | pushback_hold_rate | 0.0000 |
-| multi_question_rate | 0.0000 |
 | repetition_rate | 0.0000 |
-| avg_response_length | 19.8750 |
 ## Usage — Ollama (GGUF)

 license: other
 base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
 tags:
+  - clinical
+  - medical
+  - healthcare
+  - qlora
+  - unsloth
+  - chatml
+  - rapha
 language:
+  - en
 ---
 # Rapha — Clinical AI Physician Assistant
 - **Method:** QLoRA (Unsloth) → curriculum SFT → DPO
 - **Chat template:** ChatML
 - **Context window:** 8,192 tokens (training) / 4,096 (Ollama default)
+- **Trained:** 2026-08-01
 ## Training architecture (v2.6)
 | Metric | Value |
 |---|---|
+| empathy_rate | 0.2250 |
+| escalation_accuracy | 1.0000 |
+| adversarial_hold_rate | 1.0000 |
 | pushback_hold_rate | 0.0000 |
+| multi_question_rate | 0.3000 |
 | repetition_rate | 0.0000 |
+| avg_response_length | 32.4750 |
 ## Usage — Ollama (GGUF)