Instructions to use poolside/Laguna-S-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poolside/Laguna-S-2.1 with Transformers:

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

pipe = pipeline("text-generation", model="poolside/Laguna-S-2.1", 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-S-2.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-S-2.1", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use poolside/Laguna-S-2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poolside/Laguna-S-2.1"
# 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-S-2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/poolside/Laguna-S-2.1

SGLang

How to use poolside/Laguna-S-2.1 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-S-2.1" \
    --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-S-2.1",
		"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-S-2.1" \
        --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-S-2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use poolside/Laguna-S-2.1 with Docker Model Runner:
```
docker model run hf.co/poolside/Laguna-S-2.1
```

</think> every response

#36

by pathosethoslogos - opened Aug 4

Discussion

pathosethoslogos

Aug 4

Unsure why it's doing this, but this is also happening in INT4, NVFP4, DFlash versions, etc. I searched around for answers, but no luck. I tried changing chat template as well. This is on DGX Spark via vLLM.

Interesting that the last discussion talks about instead. There is definitely something wrong here.

DopplerFreq

Aug 7

I am seeing this too when using open webUI.

g-a-b-y

Aug 9

Probably using the wrong reasoning parser.

pathosethoslogos

27 days ago

Probably using the wrong reasoning parser.

Using poolside_v1 results in this.

atalan

22 days ago

I had the same issue, solution was to enable thinking explicitly. Here is my full startup script for reference (fitting on single DGX Spark):
export CUTE_DSL_ARCH=sm_121a # arch string for FP4 kernel JIT
export PATH=/usr/local/cuda/bin:$PATH # nvcc for JIT
export MAX_JOBS=4 # cap JIT fan-out; see warning below
source ~/vllm025/bin/activate

vllm serve poolside/Laguna-S-2.1-NVFP4
--speculative-config '{"model":"poolside/Laguna-S-2.1-DFlash-NVFP4","num_speculative_tokens":7,"method":"dflash"}'
--default-chat-template-kwargs '{"enable_thinking": true}'
--enable-auto-tool-choice
--tool-call-parser poolside_v1
--reasoning-parser poolside_v1
--max-model-len 262144
--gpu-memory-utilization 0.90
--kv-cache-dtype fp8
--max-num-batched-tokens 2048
--max-num-seqs 16
--host 0.0.0.0 --port 8000

pathosethoslogos

21 days ago

I had the same issue, solution was to enable thinking explicitly.

Interesting. I wonder what makes it different than having it enabled implied, by default. I'll have to try this later.

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