Update README.md

LICENSE.md

@@ -1,202 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright 2026 Poolside
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

README.md

@@ -7,13 +7,10 @@ extra_gated_description: >-
 tags:
 - laguna-m.1
 - vllm
-- sglang
 - fp8
 - moe
 license: apache-2.0
 pipeline_tag: text-generation
-base_model:
-- poolside/Laguna-M.1
 ---
 
 <p align="center">
@@ -28,19 +25,20 @@ base_model:
 
 <br>
 
-# Laguna M.1-FP8
+# Laguna M.1
 
-Laguna M.1-FP8 is a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token designed for agentic coding and long-horizon work. This is the FP8-quantized variant of [Laguna M.1](https://huggingface.co/poolside/Laguna-M.1).
+Laguna M.1 is a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token designed for agentic coding and long-horizon work. This release provides open weights under the Apache 2.0 license, with upstream support in vLLM, Transformers and TRT-LLM.
 
 > [!NOTE]
-> This is the FP8 variant. The [BF16](https://huggingface.co/poolside/Laguna-M.1) and [NVFP4](https://huggingface.co/poolside/Laguna-M.1-NVFP4) variants are also available on Hugging Face.
+> For more details on how we trained this model, including our Model Factory approach, post-training recipe, async off-policy agent RL, and evaluations, check out our [release blog post](https://poolside.ai/blog/laguna-a-deeper-dive) and [technical report](https://poolside.ai/assets/laguna/laguna-m1-xs2-technical-report.pdf).
 
 ## Highlights
 
-* **Large sparse MoE for agentic coding**: Laguna M.1 is a 70-layer MoE transformer with 225B total parameters and 23B activated parameters per token
+* **Large sparse MoE for agentic coding**: Laguna M.1 is a 70-layer MoE transformer with 225.8B total parameters and 23.4B activated parameters per token
 * **High-capacity expert routing**: After 3 dense SwiGLU layers, Laguna M.1 uses 67 sparse MoE layers with 256 experts, top-k=16 routing and auxiliary-loss-free load balancing
 * **Global attention architecture**: Laguna M.1 uses global attention across all layers with 64 Q-heads, 8 KV-heads and softplus attention output gating
 * **Native reasoning support**: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request
+* **Strong agentic benchmark performance**: Laguna M.1 is competitive with state-of-the-art open-weight and frontier models on SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2.0
 * **Apache 2.0 license**: Use and modify freely for commercial and non-commercial purposes
 
 ---
@@ -58,7 +56,6 @@ Laguna M.1-FP8 is a 225B total parameter Mixture-of-Experts model with 23B activ
 - Modality: text-to-text
 - Context window: 262,144 tokens
 - Reasoning support: interleaved thinking with preserved thinking
-- Quantization: FP8 (weights), detected automatically from `quantization_config`
 
 ## Benchmark results
 
@@ -66,37 +63,82 @@ Laguna M.1-FP8 is a 225B total parameter Mixture-of-Experts model with 23B activ
   <img alt="benchmarks" src="https://poolside.ai/assets/laguna/laguna-m1-chart.svg" width="800px">
 </p>
 
-| Model                     | Parameters           | SWE-bench Verified | SWE-bench Multilingual | SWE-bench Pro (Public Dataset) | Terminal-Bench 2.0 |
+| Model                     | Size (total params.) | SWE-bench Verified | SWE-bench Multilingual | SWE-bench Pro (Public Dataset) | Terminal-Bench 2.0 |
 |---------------------------|----------------------|--------------------|------------------------|--------------------------------|--------------------|
-| **Laguna M.1 (BF16)**     | 225B-A23B            | 74.6%              | 63.1%                  | 49.2%                          | 45.8%              |
+| **Laguna M.1**            | 225B                 | 74.6%              | 63.1%                  | 49.2%                          | 45.8%              |
 | Devstral 2                | 123B dense           | 72.2%              | 61.3%                  | -                              | 32.6%              |
 | GLM-4.7                   | 355B-A32B            | 73.8%              | 66.7%                  | -                              | 41.0%              |
 | DeepSeek-V4 Flash         | 284B-A13B            | 79.0%              | 73.3%                  | 52.6%                          | 56.9%              |
 | Qwen3.5-397B-A17B         | 397B-A17B            | 76.2%              | 69.3%                  | 50.9%                          | 52.5%              |
 | Claude Sonnet 4.6         | -                    | 79.6%              | -                      | -                              | 59.1%              |
 
-*Scores shown are for the BF16 reference model; see the main [Laguna M.1 model card](https://huggingface.co/poolside/Laguna-M.1) for full benchmarking methodology. We used the highest publicly-referenced scores for all comparison models across each benchmark.*
+*We used the highest publicly-referenced scores for all comparison models across each benchmark. In almost all cases these were official scores published in release blog posts or equivalent, with Claude Sonnet 4.6 shown as a frontier proprietary reference of comparable model size. “-” indicates a score not reported by the model provider.*
+
+<details>
+<summary>Expand for benchmarking methodology</summary>
+
+All benchmarking for Laguna M.1 was completed using our [pool agent harness](https://github.com/poolsideai/pool), with a maximum of 500 steps and sandboxed execution. The same sampling parameters were used for all Laguna M.1 benchmarking: temperature=1.0 and top_k=20, with thinking mode enabled and a context length of 256K tokens. All tasks were run in their own sandbox using 8 GB RAM/2 CPUs, with the exception of Terminal-Bench 2.0, which used 48 GB RAM/32 CPUs.
+
+Some base task images and verifiers were patched to fix infrastructure reliability issues inherent in task setup, such as rate limits on third-party dependencies in external registries used by the verifier. All four agentic benchmarks were run with patched images. We also ran a reward-hack judge post-hoc on Laguna M.1 evaluation runs and did not find significant reward hacking after joint judge review and manual review.
+
+- SWE-bench Verified: mean pass@1 averaged over 4 runs
+- SWE-bench Multilingual: mean pass@1 averaged over 4 runs
+- SWE-Bench Pro: mean pass@1 averaged over 4 runs
+- Terminal-Bench 2.0: mean pass@1 averaged over 4 runs; 48 GB RAM/32 CPUs
+
+</details>
 
 ## Usage
 
-Laguna M.1 has upstream support in vLLM, SGLang, and TRT-LLM thanks to the support of the team at NVIDIA.
+Laguna M.1 is available through the Poolside API and as open weights under the Apache 2.0 license.
+
+The fastest way to get started is with our API, directly or using OpenRouter.
 
 > [!NOTE]
-> For complete usage instructions, see the main [Laguna M.1 model card](https://huggingface.co/poolside/Laguna-M.1).
+> We are providing free access for a limited time to Laguna M.1 and Laguna XS.2 on our API. You can create an API key on our [Platform](https://platform.poolside.ai).
 
-### Deployment
+### pool
 
-#### vLLM
+**pool** is a lightweight terminal-based coding agent and a dual [Agent Client Protocol](https://agentclientprotocol.com/get-started) client-server.
+
+Download and install for macOS and Linux:
+
+```shell
+curl -fsSL https://downloads.poolside.ai/pool/install.sh | bash
+```
+
+Launch and *Log in with Poolside* to get a free API key.
+
+```shell
+pool
+```
 
-The full vLLM recipe is on the main [Laguna M.1 model card](https://huggingface.co/poolside/Laguna-M.1). Quantization is detected automatically from `quantization_config` in this checkpoint, so the same command works with `poolside/Laguna-M.1-FP8` substituted for the model ID. Set `VLLM_BLOCKSCALE_FP8_GEMM_FLASHINFER=0` when serving with vLLM.
+Use in any [ACP client](https://agentclientprotocol.com/get-started/clients). Configure Zed and JetBrains automatically:
 
 ```shell
-pip install 'vllm>=0.21.0'
+pool acp setup --editor zed|jetbrains
+```
+
+#### Feedback and issues
+
+Submit feedback with `/feedback` and read the [full documentation on GitHub](https://github.com/poolsideai/pool).
+
+### Local deployment
+
+Laguna M.1 is supported in vLLM and Transformers, and TRT-LLM thanks to the support of the team at NVIDIA.
 
-export VLLM_BLOCKSCALE_FP8_GEMM_FLASHINFER=0
+#### vLLM
+
+Serve Laguna M.1 locally with vLLM and query it from any OpenAI-compatible client (see [Controlling reasoning](#controlling-reasoning) for tool calls, streaming, and reasoning extraction):
+
+> [!NOTE]
+> Laguna M.1 support is available in upstream vLLM.
+
+```shell
+pip install vllm
 
 vllm serve \
-    --model poolside/Laguna-M.1-FP8 \
+    --model poolside/Laguna-M.1 \
     --tool-call-parser poolside_v1 \
     --reasoning-parser poolside_v1 \
     --enable-auto-tool-choice \
@@ -104,41 +146,199 @@ vllm serve \
     --default-chat-template-kwargs '{"enable_thinking": true}'
 ```
 
-#### SGLang
+See the [vLLM recipes page](https://recipes.vllm.ai/poolside/Laguna-XS.2) for our Laguna XS.2 model with which the implementation is shared for additional deployment guidance.
 
-The full SGLang recipe is on the [SGLang Cookbook](https://docs.sglang.io/cookbook/autoregressive/Poolside/Laguna-M.1). Quantization is detected automatically, so no extra flags are required. 
-```shell
-git clone https://github.com/sgl-project/sglang.git
-cd sglang
-pip install -e "python[all]"
+#### Transformers
 
-sglang serve \
-    --model-path poolside/Laguna-M.1-FP8 \
-    --trust-remote-code \
-    --reasoning-parser poolside_v1 \
-    --tool-call-parser poolside_v1 \
-    --tp 8 \
-    --host 0.0.0.0 \
-    --port 30000
+Laguna M.1 is supported in Transformers.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "poolside/Laguna-M.1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "user", "content": "Write a Python retry wrapper with exponential backoff."},
+]
+
+# Reasoning is on by default; pass enable_thinking=False to skip the <think> block.
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    enable_thinking=True,
+).to(model.device)
+
+outputs = model.generate(
+    inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=1,
+    top_k=20,
+)
+
+response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
+print(response)
 ```
+
 #### TRT-LLM
 
-Laguna is supported in TensorRT-LLM thanks to the team at NVIDIA ([NVIDIA/TensorRT-LLM#13559](https://github.com/NVIDIA/TensorRT-LLM/pull/13559), with partial-RoPE fusion in [#15110](https://github.com/NVIDIA/TensorRT-LLM/pull/15110)). The full recipe is on the main [Laguna M.1 model card](https://huggingface.co/poolside/Laguna-M.1). Quantization is detected automatically from `quantization_config` in this checkpoint, so no extra flags are required.
+Laguna M.1 is supported in TRT-LLM thanks to the support of the team at NVIDIA.
+
+```python
+from tensorrt_llm import LLM, SamplingParams
+
+llm = LLM(
+    model="poolside/Laguna-M.1",
+    trust_remote_code=True,
+    tensor_parallel_size=4,
+)
+
+sampling = SamplingParams(max_tokens=1024, temperature=1, top_k=20)
+out = llm.generate(["Write a Python retry wrapper with exponential backoff."], sampling)
+print(out[0].outputs[0].text)
+```
+
+Or serve with an OpenAI-compatible endpoint:
+
+```shell
+trtllm-serve poolside/Laguna-M.1 --port 8000 --trust-remote-code
+```
 
 ## Controlling reasoning
 
-Laguna M.1 has native reasoning support and is designed to work best with *preserved thinking*, where `reasoning` content from prior assistant messages is preserved in the message history. This model will generally reason before calling tools and between tool calls. See the main [Laguna M.1 model card](https://huggingface.co/poolside/Laguna-M.1#controlling-reasoning) for streaming, tool-call, and preserved-thinking examples.
+Laguna M.1 has native reasoning support and is designed to work best with *preserved thinking*, where `reasoning` content from prior assistant messages is preserved in the message history. This model will generally reason before calling tools and between tool calls.
+
+<details>
+<summary>Expand for example</summary>
+
+```python
+import json
+from openai import OpenAI
+
+client = OpenAI(
+  base_url="https://inference.poolside.ai/v1",
+  api_key="...",
+)
+
+model = "poolside/laguna-m.1"
+
+tools = [{"type": "function", "function": {
+  "name": "shell",
+  "description": "Execute a bash command and return the output.",
+  "parameters": {"type": "object", "properties": {"cmd": {"type": "string"}}, "required": ["cmd"]},
+}}]
+
+messages = [
+  {"role": "system", "content": "You are a coding agent with access to a shell tool."},
+  {"role": "user", "content": "Run uname -a"},
+]
+
+# Thinking is enabled by default when the server sets --default-chat-template-kwargs {"enable_thinking": True}
+# When using the Poolside API (https://inference.poolside.ai/v1), this flag is set by default
+response = client.chat.completions.create(
+  model=model,
+  messages=messages,
+  tools=tools,
+  stream=True,
+)
+
+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:
+    for tc in delta.tool_calls:
+      if tc.index >= len(tool_calls):
+        tool_calls.append({"id": tc.id, "function": {"name": "", "arguments": ""}})
+      if tc.function.name:
+        tool_calls[tc.index]["function"]["name"] = tc.function.name
+      if tc.function.arguments:
+        tool_calls[tc.index]["function"]["arguments"] += tc.function.arguments
+
+print(f"Reasoning: {reasoning}\nContent: {content}\nTool calls: {tool_calls}\n")
+
+# Return reasoning in the next request for best performance
+messages.append({
+  "role": "assistant",
+  "content": content,
+  "reasoning_content": reasoning,
+  "tool_calls": [{"id": tc["id"], "type": "function", "function": tc["function"]} for tc in tool_calls]
+})
+
+messages.append({
+  "role": "tool",
+  "tool_call_id": tool_calls[0]["id"],
+  "content": json.dumps({"stdout": "Darwin arm64", "exit_code": "0"})
+})
+
+response = client.chat.completions.create(
+  model=model,
+  messages=messages,
+  tools=tools,
+  stream=True,
+)
+
+reasoning, content = "", ""
+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
+
+print(f"Reasoning: {reasoning}\nContent: {content}")
+```
+
+</details>
 
 ### Disabling reasoning
 
 You can disable thinking by setting `enable_thinking` to `False` in a request or by not providing `--default-chat-template-kwargs {"enable_thinking": True}` or equivalent when starting the server.
 
+<details>
+<summary>Expand for example</summary>
+
+```python
+from openai import OpenAI
+client = OpenAI()
+
+completion = client.chat.completions.create(
+  model="poolside/laguna-m.1",
+  messages=[
+    {"role": "user", "content": "Write a retry wrapper with exponential backoff."}
+  ],
+  extra_body={
+    "chat_template_kwargs": { "enable_thinking": False },
+  },
+  stream=True
+)
+
+for chunk in completion:
+    print(chunk.choices[0].delta)
+```
+
+</details>
+
+For agentic coding use cases, we recommend enabling thinking and preserving reasoning in message history as outlined in the [Controlling reasoning](#controlling-reasoning) section.
+
 ## License
 
-This model is licensed under the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.1-FP8/blob/main/LICENSE.md).
+This model is licensed under the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.1/blob/main/LICENSE.md).
 
-## Intended and Responsible Use
+## Intended and Responsible Use 
 
-Laguna M.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 M.1 is subject to the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.1-FP8/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 M.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
+Laguna M.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 M.1 is subject to the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.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 M.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
 
 Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).

generation_config.json

@@ -9,10 +9,5 @@
   "pad_token_id": 9,
   "temperature": 1.0,
   "top_p": 1.0,
-  "min_p": 0.0,
-  "tool_call_parser": "poolside_v1",
-  "reasoning_parser": "poolside_v1",
-  "default_chat_template_kwargs": {
-    "enable_thinking": true
-  }
-}
+  "min_p": 0.0
+}

tokenizer_config.json

@@ -571,5 +571,6 @@
   "pad_token": "〈|PAD|〉",
   "sep_token": "〈|SEP|〉",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "〈|UNK|〉"
-}
+  "unk_token": "〈|UNK|〉",
+  "chat_template": "{% include 'chat_template.jinja' %}"
+}