Instructions to use CapPow/herb-visor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CapPow/herb-visor with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CapPow/herb-visor",
	filename="herb-visor-4b-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CapPow/herb-visor 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 CapPow/herb-visor:F16
# Run inference directly in the terminal:
llama cli -hf CapPow/herb-visor:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CapPow/herb-visor:F16
# Run inference directly in the terminal:
llama cli -hf CapPow/herb-visor:F16

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 CapPow/herb-visor:F16
# Run inference directly in the terminal:
./llama-cli -hf CapPow/herb-visor:F16

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 CapPow/herb-visor:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CapPow/herb-visor:F16

Use Docker

docker model run hf.co/CapPow/herb-visor:F16

LM Studio
Jan

vLLM

How to use CapPow/herb-visor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CapPow/herb-visor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CapPow/herb-visor",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CapPow/herb-visor:F16

Ollama
How to use CapPow/herb-visor with Ollama:
```
ollama run hf.co/CapPow/herb-visor:F16
```

Unsloth Studio

How to use CapPow/herb-visor 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 CapPow/herb-visor 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 CapPow/herb-visor to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CapPow/herb-visor to start chatting

Atomic Chat new
Docker Model Runner
How to use CapPow/herb-visor with Docker Model Runner:
```
docker model run hf.co/CapPow/herb-visor:F16
```

Lemonade

How to use CapPow/herb-visor with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CapPow/herb-visor:F16

Run and chat with the model

lemonade run user.herb-visor-F16

List all available models

lemonade list

CapPow commited on 29 days ago

Commit

5488f7a

verified ·

1 Parent(s): 0621363

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -16

README.md CHANGED Viewed

@@ -29,29 +29,27 @@ Given a specimen image and its taxon name, the model returns schema-valid JSON w
 - **Format:** GGUF (llama.cpp-native), runs offline on an 8 GB-class GPU
 - **Code, validation, and documentation:** [GitHub repository](https://github.com/CapPow/herb-visor)
-## Files
-| File | Purpose |
-|---|---|
-| `herb-visor-4b-q8.gguf` | model weights, q8 (recommended; runs in ~8 GB VRAM) |
-| `herb-visor-4b-f16.gguf` | model weights, f16 |
-| `herb-visor-4b-mmproj-f16.gguf` | vision projector (required for image input) |
-The mmproj file is required. Pair it with either weight file.
-## Recommended download
-- Weights (Q8 recommended): [`herb-visor-4b-q8.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-q8.gguf?download=true)
-- Vision projector (required): [`herb-visor-4b-mmproj-f16.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-mmproj-f16.gguf?download=true)
-- F16: [`herb-visor-4b-f16.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-f16.gguf?download=true)
-One-line pull via llama.cpp (resolves to Q8):
-  llama-server -hf CapPow/herb-visor:Q8 --mmproj herb-visor-4b-mmproj-f16.gguf
-## Usage
-Start a server with llama.cpp:
 ```bash
 llama-server \

 - **Format:** GGUF (llama.cpp-native), runs offline on an 8 GB-class GPU
 - **Code, validation, and documentation:** [GitHub repository](https://github.com/CapPow/herb-visor)
+## Quickstart (recommended)
+One command — downloads Q8 to llama.cpp's cache and auto-fetches the projector:
+```bash
+llama-server -hf CapPow/herb-visor:Q8 --temp 0 -c 8192
+```
+Serves an OpenAI-compatible endpoint at `127.0.0.1:8080`.
+## Manual download (alternative)
+Only needed for offline/air-gapped use or to pin a specific file. The pull above already handles downloads, so don't do both. Download the projector (required) plus one weight file:
+| File | Purpose |
+|---|---|
+| [`herb-visor-4b-mmproj-f16.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-mmproj-f16.gguf?download=true) | vision projector — **required** for image input |
+| [`herb-visor-4b-q8.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-q8.gguf?download=true) | model weights, q8 (**recommended**; ~8 GB VRAM) |
+| [`herb-visor-4b-f16.gguf`](https://huggingface.co/CapPow/herb-visor/resolve/main/herb-visor-4b-f16.gguf?download=true) | model weights, f16 |
+Pair the mmproj with either weight file, then run against the local files:
 ```bash
 llama-server \