Text Generation
Transformers
Safetensors
laguna
laguna-s-2.1
vllm
conversational
custom_code
Eval Results
Instructions to use poolside/Laguna-S-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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)# pip install -U transformers accelerate # 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=256) 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
Apply OpenMDW-1.1 license and responsible-use disclaimer (as XS 2.1)
Browse files
README.md
CHANGED
|
@@ -1,9 +1,13 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
inference: false
|
|
|
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
- laguna-s-2.1
|
| 6 |
- vllm
|
|
|
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
---
|
| 9 |
|
|
@@ -11,7 +15,7 @@ pipeline_tag: text-generation
|
|
| 11 |
|
| 12 |
> [!IMPORTANT]
|
| 13 |
> Private preview. This repository and the rest of the Laguna S 2.1 family are not
|
| 14 |
-
> yet public.
|
| 15 |
|
| 16 |
Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated
|
| 17 |
parameters per token, designed for agentic coding and long-horizon work. It sits
|
|
@@ -36,6 +40,9 @@ expert, grouped-query attention, and interleaved full/sliding-window attention.
|
|
| 36 |
[NVFP4](https://huggingface.co/poolside/Laguna-S-2.1-NVFP4),
|
| 37 |
[INT4](https://huggingface.co/poolside/Laguna-S-2.1-INT4) and
|
| 38 |
[GGUF](https://huggingface.co/poolside/Laguna-S-2.1-GGUF)
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
## Model overview
|
| 41 |
|
|
@@ -131,9 +138,12 @@ or at the server level with
|
|
| 131 |
use cases we recommend enabling thinking and preserving reasoning in the message
|
| 132 |
history.
|
| 133 |
|
| 134 |
-
##
|
| 135 |
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
inference: false
|
| 4 |
+
extra_gated_description: >-
|
| 5 |
+
To learn more about how we process your personal data, please read our <a
|
| 6 |
+
href="https://poolside.ai/legal/privacy">Privacy Policy</a>.
|
| 7 |
tags:
|
| 8 |
- laguna-s-2.1
|
| 9 |
- vllm
|
| 10 |
+
license: openmdw-1.1
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
---
|
| 13 |
|
|
|
|
| 15 |
|
| 16 |
> [!IMPORTANT]
|
| 17 |
> Private preview. This repository and the rest of the Laguna S 2.1 family are not
|
| 18 |
+
> yet public.
|
| 19 |
|
| 20 |
Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated
|
| 21 |
parameters per token, designed for agentic coding and long-horizon work. It sits
|
|
|
|
| 40 |
[NVFP4](https://huggingface.co/poolside/Laguna-S-2.1-NVFP4),
|
| 41 |
[INT4](https://huggingface.co/poolside/Laguna-S-2.1-INT4) and
|
| 42 |
[GGUF](https://huggingface.co/poolside/Laguna-S-2.1-GGUF)
|
| 43 |
+
- **OpenMDW-1.1 license**: Use and modify the model and associated materials freely
|
| 44 |
+
for commercial and non-commercial purposes
|
| 45 |
+
([learn more about OpenMDW](https://openmdw.ai/))
|
| 46 |
|
| 47 |
## Model overview
|
| 48 |
|
|
|
|
| 138 |
use cases we recommend enabling thinking and preserving reasoning in the message
|
| 139 |
history.
|
| 140 |
|
| 141 |
+
## License
|
| 142 |
|
| 143 |
+
This model is licensed under the [OpenMDW-1.1 License](https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md).
|
| 144 |
+
|
| 145 |
+
## Intended and Responsible Use
|
| 146 |
+
|
| 147 |
+
Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
|
| 148 |
+
|
| 149 |
+
Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).
|