Instructions to use Docglasses-AI/llama32-soap-e2-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Docglasses-AI/llama32-soap-e2-gguf 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 Docglasses-AI/llama32-soap-e2-gguf:Q6_K
# Run inference directly in the terminal:
llama cli -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K
# Run inference directly in the terminal:
llama cli -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

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 Docglasses-AI/llama32-soap-e2-gguf:Q6_K
# Run inference directly in the terminal:
./build/bin/llama cli -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Use Docker

docker model run hf.co/Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Llama new
LM Studio
Jan
Ollama
How to use Docglasses-AI/llama32-soap-e2-gguf with Ollama:
```
ollama run hf.co/Docglasses-AI/llama32-soap-e2-gguf:Q6_K
```
Unsloth Desktop

How to use Docglasses-AI/llama32-soap-e2-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Docglasses-AI/llama32-soap-e2-gguf:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Docglasses-AI/llama32-soap-e2-gguf with Docker Model Runner:
```
docker model run hf.co/Docglasses-AI/llama32-soap-e2-gguf:Q6_K
```

Lemonade

How to use Docglasses-AI/llama32-soap-e2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Run and chat with the model

lemonade run user.llama32-soap-e2-gguf-Q6_K

List all available models

lemonade list

Hermes Agent

How to use Docglasses-AI/llama32-soap-e2-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Docglasses-AI/llama32-soap-e2-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Docglasses-AI/llama32-soap-e2-gguf:Q6_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Docglasses-AI/llama32-soap-e2-gguf:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Llama 3.2 1B SOAP (e2) — Q6_K GGUF (mobile)

Llama 3.2 1B Instruct fine-tuned to write a SOAP note (Subjective, Objective, Assessment, Plan) from one doctor-patient consultation transcript. Used for the on-device clinical summary in the DocGlasses Android app.

Research use only. Not a medical device. Notes must be reviewed by a clinician.

Files

File	Bytes	Role
`llama32-soap-e2-Q6_K.gguf`	1021800128	The model (Q6_K, closest to the merged bf16 weights)
`llama32_mobile_config.json`		Filenames, context, threads, stop tokens, `prompt: e2`
`soap_prompt.ts`		e2/e3 prompts, parser, plan grounding, `assembleFinalSummary`

Runtime

Context 4096; max new tokens 896; temperature 0; 4 CPU threads.
Clip the transcript to 3500 characters (first 1750 + \n...\n + last 1750).
Llama 3.2 chat template with no date header; stop on <|eot_id|> and <|end_of_text|>.
e2 output is four plain blocks: Subjective:, Objective:, Assessment:, Plan:. Never ask it for JSON.
After generation run parseFields(raw) then assembleFinalSummary(fields, dialogue) with the full transcript, and show only the assembled fields. Plan grounding removes invented orders and medications.

License

Downloads last month: 86

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Docglasses-AI/llama32-soap-e2-gguf

Base model

meta-llama/Llama-3.2-1B-Instruct

Quantized

(432)

this model