Instructions to use multimodalart/laguna-s-2.1-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use multimodalart/laguna-s-2.1-DFlash with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="multimodalart/laguna-s-2.1-DFlash",
	filename="laguna-s-2.1-DFlash-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use multimodalart/laguna-s-2.1-DFlash 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 multimodalart/laguna-s-2.1-DFlash:Q8_0
# Run inference directly in the terminal:
llama cli -hf multimodalart/laguna-s-2.1-DFlash:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf multimodalart/laguna-s-2.1-DFlash:Q8_0
# Run inference directly in the terminal:
llama cli -hf multimodalart/laguna-s-2.1-DFlash:Q8_0

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 multimodalart/laguna-s-2.1-DFlash:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf multimodalart/laguna-s-2.1-DFlash:Q8_0

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 multimodalart/laguna-s-2.1-DFlash:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf multimodalart/laguna-s-2.1-DFlash:Q8_0

Use Docker

docker model run hf.co/multimodalart/laguna-s-2.1-DFlash:Q8_0

LM Studio
Jan
Ollama
How to use multimodalart/laguna-s-2.1-DFlash with Ollama:
```
ollama run hf.co/multimodalart/laguna-s-2.1-DFlash:Q8_0
```

Unsloth Studio

How to use multimodalart/laguna-s-2.1-DFlash 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 multimodalart/laguna-s-2.1-DFlash 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 multimodalart/laguna-s-2.1-DFlash to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for multimodalart/laguna-s-2.1-DFlash to start chatting

Atomic Chat new
Docker Model Runner
How to use multimodalart/laguna-s-2.1-DFlash with Docker Model Runner:
```
docker model run hf.co/multimodalart/laguna-s-2.1-DFlash:Q8_0
```

Lemonade

How to use multimodalart/laguna-s-2.1-DFlash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull multimodalart/laguna-s-2.1-DFlash:Q8_0

Run and chat with the model

lemonade run user.laguna-s-2.1-DFlash-Q8_0

List all available models

lemonade list

Can't run due to wrong tensor count

by Noiita - opened 5 days ago

Discussion

Noiita

5 days ago

•

edited 5 days ago

As stated in topic, issue persists over both Q8 and BF16 variants.
Runned on latest poolside's llama.cpp fork.

E llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 76, got 69
E llama_model_load_from_file_impl: failed to load model
E common_speculative_init_result: failed to load draft model, '/home/username/models/un
sloth/laguna/laguna-s-2.1-DFlash-Q8_0-fixed.gguf'

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment