joerowell commited on
Commit
f2ba500
·
verified ·
1 Parent(s): 1c36e52

Apply OpenMDW-1.1 license and responsible-use disclaimer (as XS 2.1)

Browse files
Files changed (1) hide show
  1. README.md +16 -6
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. Licensing and external distribution are TBD.
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
- ## Intended use
135
 
136
- Laguna S 2.1 is designed for software engineering and agentic coding use cases.
137
- This is a private preview; do not distribute externally until licensing is
138
- finalised. Please report security vulnerabilities or safety concerns to
139
- [security@poolside.ai](mailto:security@poolside.ai).
 
 
 
 
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).