Instructions to use poolside-laguna-hackathon/Laguna-XS.2-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 poolside-laguna-hackathon/Laguna-XS.2-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 poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF: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 poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF: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 poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Use Docker

docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

LM Studio
Jan

vLLM

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poolside-laguna-hackathon/Laguna-XS.2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poolside-laguna-hackathon/Laguna-XS.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Ollama
How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Ollama:
```
ollama run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Docker Model Runner:
```
docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
```

Lemonade

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Run and chat with the model

lemonade run user.Laguna-XS.2-GGUF-F16

List all available models

lemonade list

Atomic Chat

Saurabh-66 commited on May 30

Commit

809c8d1

verified ·

1 Parent(s): 7e3a37e

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -7

README.md CHANGED Viewed

@@ -60,6 +60,14 @@ All benchmarks: H200 MIG 71GB, vLLM 0.21.0, BF16, temperature=0.
 | Single request | 57–74 |
 | 5 concurrent | 100–106 |
 ## Architecture - Key Differences from Mixtral
 | Feature | Laguna XS.2 | Mixtral |
@@ -74,13 +82,16 @@ All benchmarks: H200 MIG 71GB, vLLM 0.21.0, BF16, temperature=0.
 | Q-heads per layer | **48 (GA) / 64 (SWA)** | Uniform |
 ### Custom GGUF Metadata Keys
-|laguna.attention.layer_types      |[0,1,1,1,0,...] GA=0 SWA=1|
-|laguna.attention.heads_per_layer  |[48,64,64,64,48,...]|
-|laguna.rope.theta_swa             |10000.0|
-|laguna.rope.partial_rotary_factor |0.5|
-|laguna.moe.routed_scaling_factor  |2.5|
-|laguna.moe.sigmoid_routing        |true|
-|laguna.attention.softplus_gating  |true|
 ## C++ Patches for llama.cpp Inference

 | Single request | 57–74 |
 | 5 concurrent | 100–106 |
+## Benchmark Visualizations
+![Capability Benchmarks](images/capability_benchmarks.png)
+![Throughput](images/throughput.png)
+![MATH500 by Subject](images/math500_by_subject.png)
 ## Architecture - Key Differences from Mixtral
 | Feature | Laguna XS.2 | Mixtral |
 | Q-heads per layer | **48 (GA) / 64 (SWA)** | Uniform |
 ### Custom GGUF Metadata Keys
+| Key | Value |
+|-----|-------|
+| `laguna.attention.layer_types` | `[0,1,1,1,0,...]` — GA=0, SWA=1 |
+| `laguna.attention.heads_per_layer` | `[48,64,64,64,48,...]` |
+| `laguna.rope.theta_swa` | `10000.0` |
+| `laguna.rope.partial_rotary_factor` | `0.5` |
+| `laguna.moe.routed_scaling_factor` | `2.5` |
+| `laguna.moe.sigmoid_routing` | `true` |
+| `laguna.attention.softplus_gating` | `true` |
 ## C++ Patches for llama.cpp Inference