Instructions to use poolside/Laguna-XS.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poolside/Laguna-XS.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="poolside/Laguna-XS.2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("poolside/Laguna-XS.2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-XS.2", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poolside/Laguna-XS.2"
# 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-XS.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/poolside/Laguna-XS.2

SGLang

How to use poolside/Laguna-XS.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "poolside/Laguna-XS.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poolside/Laguna-XS.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "poolside/Laguna-XS.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poolside/Laguna-XS.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use poolside/Laguna-XS.2 with Docker Model Runner:
```
docker model run hf.co/poolside/Laguna-XS.2
```

varunrandery commited on Apr 27

Commit

afed5b9

verified ·

1 Parent(s): 825ca3a

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -12

README.md CHANGED Viewed

@@ -1,11 +1,9 @@
 ---
 library_name: vllm
 inference: false
-base_model:
-- poolside/Laguna-XS.2-base
 extra_gated_description: >-
   To learn more about how we process your personal data, please read our <a
-  href="https://poolside.ai/privacy">Privacy Policy</a>.
 tags:
 - laguna-xs.2
 license: apache-2.0
@@ -28,9 +26,7 @@ pipeline_tag: text-generation
 Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 30 out of 40 layers for fast inference and low KV cache requirements.
 > [!NOTE]
-> This is the final model with native reasoning support and interleaved thinking. For the base model, see [Laguna XS.2-base](https://huggingface.co/poolside/Laguna-XS.2-base).
-For more details on how we trained this model, including on data automixing and async off-policy agent RL, check out our [release blog post](https://poolside.ai/blog/laguna-a-deeper-dive).
 ## Highlights
 - **Mixed SWA and global attention layout**: Laguna XS.2 uses sigmoid gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 40 total layers)
@@ -51,7 +47,7 @@ For more details on how we trained this model, including on data automixing and
 - Sliding Window: 512 tokens
 - Modality: text-to-text
 - Context window: 131,072 tokens
-- Reasoning support: thinking default enabled; interleaved thinking with preserved thinking supported
 ## Benchmark results
@@ -107,8 +103,6 @@ Launch and *Log in with Poolside* to get a free API key.
 pool
 ```
-[Placeholder for screenshot]
 Use in any [ACP client](https://agentclientprotocol.com/get-started/clients). Configure Zed and JetBrains automatically:
 ```shell
@@ -187,8 +181,8 @@ response = client.chat.completions.create(
 reasoning, content, tool_calls = "", "", []
 for chunk in response:
   delta = chunk.choices[0].delta
-  if hasattr(delta, "reasoning") and delta.reasoning:
-    reasoning += delta.reasoning
   if hasattr(delta, "content") and delta.content:
     content += delta.content
   if hasattr(delta, "tool_calls") and delta.tool_calls:
@@ -206,7 +200,7 @@ print(f"Reasoning: {reasoning}\nContent: {content}\nTool calls: {tool_calls}\n")
 messages.append({
   "role": "assistant",
   "content": content,
-  "reasoning": reasoning,
   "tool_calls": [{"id": tc["id"], "type": "function", "function": tc["function"]} for tc in tool_calls]
 })

 ---
 library_name: vllm
 inference: false
 extra_gated_description: >-
   To learn more about how we process your personal data, please read our <a
+  href="https://poolside.ai/legal/privacy">Privacy Policy</a>.
 tags:
 - laguna-xs.2
 license: apache-2.0
 Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 30 out of 40 layers for fast inference and low KV cache requirements.
 > [!NOTE]
+> For more details on how we trained this model, including on data automixing and async off-policy agent RL, check out our [release blog post](https://poolside.ai/blog/laguna-a-deeper-dive).
 ## Highlights
 - **Mixed SWA and global attention layout**: Laguna XS.2 uses sigmoid gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 40 total layers)
 - Sliding Window: 512 tokens
 - Modality: text-to-text
 - Context window: 131,072 tokens
+- Reasoning support: interleaved thinking with preserved thinking
 ## Benchmark results
 pool
 ```
 Use in any [ACP client](https://agentclientprotocol.com/get-started/clients). Configure Zed and JetBrains automatically:
 ```shell
 reasoning, content, tool_calls = "", "", []
 for chunk in response:
   delta = chunk.choices[0].delta
+  if hasattr(delta, "reasoning_content") and delta.reasoning_content:
+    reasoning += delta.reasoning_content
   if hasattr(delta, "content") and delta.content:
     content += delta.content
   if hasattr(delta, "tool_calls") and delta.tool_calls:
 messages.append({
   "role": "assistant",
   "content": content,
+  "reasoning_content": reasoning,
   "tool_calls": [{"id": tc["id"], "type": "function", "function": tc["function"]} for tc in tool_calls]
 })