Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+others.jpg filter=lfs diff=lfs merge=lfs -text
+editing.jpg filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+realism.jpg filter=lfs diff=lfs merge=lfs -text
+text_encoder/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+flux2_klein_fp8.png filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1768503384

LICENSE.md

@@ -0,0 +1,176 @@
+                             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

README.md

@@ -0,0 +1,130 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: image-to-image
+tags:
+- text-to-image
+- image-editing
+- flux
+- diffusion-single-file
+---
+
+![Teaser](./flux2_klein_fp8.png)
+
+The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, **delivering state-of-the-art quality with end-to-end inference in as low as under a second**. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware, with as little as 13GB VRAM.
+
+FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.
+
+Fully open under Apache 2.0. Our most accessible model runs on consumer GPUs like the RTX 3090/4070. Compact but capable: supports text-to-image, image editing, and multi-reference at quality that punches above its size. Built for local development, edge deployment, and production use.
+
+For more information, please read our [blog post](https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence).
+
+## **Quantization Details 🔧**
+
+This model is a quantized version optimized for efficient inference:
+
+- **Transformer**: Quantized using TorchAo fp8  (float8wo) quantization, significantly reducing model size while maintaining generation quality.
+- **Text Encoder**: Replaced with `unsloth/Qwen3-4B-unsloth-bnb-4bit`, a 4-bit quantized version that further reduces memory requirements.
+- **Memory Usage**: Peak VRAM consumption is approximately **9GB**.
+- **Performance**: Generates images in approximately **0.1 seconds** (4 steps)on RTX 5090 GPUs.
+
+
+## **Using with Diffusers 🧨**
+
+To use FLUX.2 [klein] 4B with the 🧨 Diffusers python library, first install or upgrade diffusers:
+
+```shell
+pip install -U diffusers
+```
+Then you can use Flux2KleinPipeline to run the model:
+
+```python
+import os
+import torch
+from diffusers import Flux2KleinPipeline, Flux2Transformer2DModel
+
+model_dir = "."
+model_path = f"{model_dir}/FLUX.2-klein-4B-int8-diffusers"
+prompt = "A cat holding a sign that says hello Tonera"
+height, width, guidance_scale, steps, seed = 1024, 1024, 4.0, 4, 0
+dtype = torch.bfloat16
+
+transformer = Flux2Transformer2DModel.from_pretrained(
+    f"{model_path}/transformer",
+    torch_dtype=dtype,
+    use_safetensors=False,
+)
+
+pipe = Flux2KleinPipeline.from_pretrained(
+    f"{model_path}", 
+    torch_dtype=dtype, 
+    transformer=transformer, 
+)
+pipe.to("cuda")
+
+img = pipe(
+    prompt=prompt,
+    height=height,
+    width=width,
+    guidance_scale=guidance_scale,
+    num_inference_steps=steps,
+    generator=torch.Generator(device="cuda").manual_seed(seed),
+).images[0]
+
+output = "output/flux2_klein.png"
+os.makedirs(os.path.dirname(output) or ".", exist_ok=True)
+img.save(output)
+print(output)
+```
+
+
+---
+Limitations
+
+- This model is not intended or able to provide factual information.
+- While the model can output text, text rendered may be inaccurate or subject to distortion.
+- As a statistical model, this checkpoint may represent or amplify biases observed in the training data.
+- The model may fail to generate output that matches the prompts.
+- Prompt following is heavily influenced by the prompting style.
+
+Out-of-Scope Use
+
+The model and its derivatives may not be used:
+
+- In any way that violates applicable law.
+- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content.
+- To generate or disseminate deceptive, fraudulent, misleading or otherwise harmful content.
+- To generate or disseminate personal identifiable information that can be used to harm an individual.
+- To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.
+- To create non-consensual intimate imagery or illegal pornographic content.
+- For fully automated decision making or high risk applications that adversely impact an individual's legal rights or otherwise create or modify a binding, enforceable obligation.
+
+Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.
+
+Hardware
+
+The FLUX.2 [klein] 4B model fits in ~13GB VRAM and is accessible on NVIDIA RTX 3090/4070 and above.
+
+---
+Responsible AI Development
+
+Black Forest Labs is committed to the responsible development and deployment of our models. Prior to releasing the FLUX.2 family of models, we evaluated and mitigated a number of risks in our model checkpoints and hosted services, including the generation of unlawful content, including child sexual abuse material (CSAM) and nonconsensual intimate imagery (NCII). We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks:
+
+1. Pre-training mitigation. We filtered pre-training data for multiple categories of "not safe for work" (NSFW) and known child sexual abuse material (CSAM) to help prevent a user generating unlawful content in response to text prompts or uploaded images. We have partnered with the https://www.iwf.org.uk/, an independent nonprofit organization dedicated to preventing online abuse, to filter known CSAM from the training data.
+2. Post-training mitigation. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse, including both text-to-image (T2I) and image-to-image (I2I) attacks. By inhibiting certain behaviors and suppressing certain concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or NCII from a text prompt, or transforming an uploaded image into synthetic CSAM or NCII.
+3. Ongoing evaluation. Throughout this process, we conducted multiple internal and external third-party evaluations of model checkpoints to identify further opportunities for mitigation. External third-party evaluations focused on eliciting CSAM and NCII through adversarial testing with (i) text-only prompts, (ii) a single uploaded reference image with text prompts, and (iii) multiple uploaded reference images with text prompts. Based on this feedback, we conducted further safety fine-tuning to produce our open-weight FLUX.2 [klein] models.
+4. Release decision. After safety fine-tuning and prior to release, we conducted a final third-party evaluation of the proposed release checkpoints, focused on T2I and I2I generation of synthetic CSAM and NCII, including a comparison with other open-weight T2I and I2I models. The final FLUX.2 [klein] checkpoints demonstrated high resilience against violative inputs in complex generation and editing tasks, and demonstrated higher resilience than leading open-weight models across these risk categories. Based on these findings, we approved the release of the open-weight FLUX.2 [klein] 4B models under an Apache 2.0 license and the release of the FLUX.2 [klein] 9B models under a non-commercial license to support third-party research and development.
+5. Inference filters. The repository for the FLUX.2 [klein] models includes filters for NSFW and protected content in inputs and outputs. Filters or manual review must be used with the FLUX.2 [klein] 9B models under the terms of the FLUX Non-Commercial License, and we encourage deployers to implement these mitigations when using the FLUX.2 [klein] 4B models. Where we implement these features on our own hosted services, we may apply multiple filters to intercept text prompts, uploaded images, and output images. We utilize both in-house and third-party filters to mitigate against harmful outputs, such as CSAM and NCII outputs, including filters provided by https://thehive.ai/ and https://www.microsoft.com/.
+6. Content provenance. Content provenance features can help users and platforms better identify, label, and interpret AI-generated content online. The inference code for FLUX.2 [klein] implements an example of pixel-layer watermarking. Additionally, this repository includes links to the https://c2pa.org/ standard for metadata. The API for FLUX.2 [klein] applies cryptographically-signed C2PA metadata to downloaded output content to indicate that images were produced with our model.
+7. Policies. Acceptable use of our models and access to our API are governed by policies set out in applicable documentation, including FLUX Non-Commercial License (for our non-commercial open-weight users); Developer Terms of Service, Self-Hosted Commercial License Terms, and Usage Policy (for our commercial open-weight model users); and Developer Terms of Service, FLUX API Service Terms, and Usage Policy (for our API users). These prohibit the generation of unlawful content or the use of generated content for unlawful, defamatory, or abusive purposes.
+8. Safety. Black Forest Labs takes model safety seriously. We provide a dedicated email address (safety@blackforestlabs.ai) to solicit feedback from the community. We maintain a reporting relationship with organizations such as the https://www.iwf.org.uk/ and the https://www.missingkids.org/, and welcome ongoing engagement with authorities, developers, and researchers to share intelligence about emerging risks and develop effective mitigations.
+
+---
+License
+
+This model is licensed under the https://www.apache.org/licenses/LICENSE-2.0.
+
+Trademarks & IP
+
+This project may contain trademarks or logos for projects, products, or services. Use of Black Forest Labs and FLUX trademarks or logos in modified versions of this project must not cause confusion or imply sponsorship or endorsement. Any use of third-party trademarks, intellectual property or logos are subject to those third-party's policies.

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-to-image", "allow_remote": true}

model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "Flux2KleinPipeline",
+  "_diffusers_version": "0.37.0.dev0",
+  "is_distilled": true,
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3ForCausalLM"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "Flux2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLFlux2"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.37.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 3.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/README.md

@@ -0,0 +1,385 @@
+---
+base_model: Qwen/Qwen3-4B
+language:
+- en
+library_name: transformers
+license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE
+license: apache-2.0
+tags:
+- qwen3
+- qwen
+- unsloth
+- transformers
+---
+<div>
+  <p style="margin-bottom: 0; margin-top: 0;">
+    <strong>See <a href="https://huggingface.co/collections/unsloth/qwen3-680edabfb790c8c34a242f95">our collection</a> for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.</strong>
+  </p>
+  <p style="margin-bottom: 0;">
+    <em>Learn to run Qwen3 correctly - <a href="https://docs.unsloth.ai/basics/qwen3-how-to-run-and-fine-tune">Read our Guide</a>.</em>
+  </p>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+<h1 style="margin-top: 0rem;">✨ Run & Fine-tune Qwen3 with Unsloth!</h1>
+</div>
+
+- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
+- Read our Blog about Qwen3 support: [unsloth.ai/blog/qwen3](https://unsloth.ai/blog/qwen3)
+- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
+- Run & export your fine-tuned model to Ollama, llama.cpp or HF.
+
+| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
+|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
+| **Qwen3 (14B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 3x faster | 70% less |
+| **GRPO with Qwen3 (8B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 3x faster | 80% less |
+| **Llama-3.2 (3B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb)               | 2.4x faster | 58% less |
+| **Llama-3.2 (11B vision)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 2x faster | 60% less |
+| **Qwen2.5 (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb)               | 2x faster | 60% less |
+| **Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb)               | 2x faster | 50% less |
+
+# Qwen3-4B
+
+## Qwen3 Highlights
+
+Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
+
+- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
+- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
+- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
+- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
+- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
+
+## Model Overview
+
+**Qwen3-4B** has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Number of Parameters: 4.0B
+- Number of Paramaters (Non-Embedding): 3.6B
+- Number of Layers: 36
+- Number of Attention Heads (GQA): 32 for Q and 8 for KV
+- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts). 
+
+For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## Quickstart
+
+The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.51.0`, you will encounter the following error:
+```
+KeyError: 'qwen3'
+```
+
+The following contains a code snippet illustrating how to use the model generate content based on given inputs. 
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen3-4B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+For deployment, you can use `vllm>=0.8.5` or `sglang>=0.4.5.post2` to create an OpenAI-compatible API endpoint:
+- vLLM:
+    ```shell
+    vllm serve Qwen/Qwen3-4B --enable-reasoning --reasoning-parser deepseek_r1
+    ```
+- SGLang:
+    ```shell
+    python -m sglang.launch_server --model-path Qwen/Qwen3-4B --reasoning-parser deepseek-r1
+    ```
+
+## Switching Between Thinking and Non-Thinking Mode
+
+> [!TIP]
+> The `enable_thinking` switch is also available in APIs created by vLLM and SGLang. 
+> Please refer to [our documentation](https://qwen.readthedocs.io/) for more details.
+
+### `enable_thinking=True`
+
+By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
+
+```python
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True  # True is the default value for enable_thinking
+)
+```
+
+In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
+
+> [!NOTE]
+> For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
+
+
+### `enable_thinking=False`
+
+We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
+
+```python
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=False  # Setting enable_thinking=False disables thinking mode
+)
+```
+
+In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
+
+> [!NOTE]
+> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
+
+### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
+
+We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
+
+Here is an example of a multi-turn conversation:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+class QwenChatbot:
+    def __init__(self, model_name="Qwen/Qwen3-4B"):
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name)
+        self.history = []
+
+    def generate_response(self, user_input):
+        messages = self.history + [{"role": "user", "content": user_input}]
+
+        text = self.tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+
+        inputs = self.tokenizer(text, return_tensors="pt")
+        response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
+        response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
+
+        # Update history
+        self.history.append({"role": "user", "content": user_input})
+        self.history.append({"role": "assistant", "content": response})
+
+        return response
+
+# Example Usage
+if __name__ == "__main__":
+    chatbot = QwenChatbot()
+
+    # First input (without /think or /no_think tags, thinking mode is enabled by default)
+    user_input_1 = "How many r's in strawberries?"
+    print(f"User: {user_input_1}")
+    response_1 = chatbot.generate_response(user_input_1)
+    print(f"Bot: {response_1}")
+    print("----------------------")
+
+    # Second input with /no_think
+    user_input_2 = "Then, how many r's in blueberries? /no_think"
+    print(f"User: {user_input_2}")
+    response_2 = chatbot.generate_response(user_input_2)
+    print(f"Bot: {response_2}") 
+    print("----------------------")
+
+    # Third input with /think
+    user_input_3 = "Really? /think"
+    print(f"User: {user_input_3}")
+    response_3 = chatbot.generate_response(user_input_3)
+    print(f"Bot: {response_3}")
+```
+
+> **Note**
+> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
+> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
+
+## Agentic Use
+
+Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
+
+To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
+```python
+import os
+from qwen_agent.agents import Assistant
+
+# Define LLM
+llm_cfg = {
+    'model': 'Qwen3-4B',
+
+    # Use the endpoint provided by Alibaba Model Studio:
+    # 'model_type': 'qwen_dashscope',
+    # 'api_key': os.getenv('DASHSCOPE_API_KEY'),
+
+    # Use a custom endpoint compatible with OpenAI API:
+    'model_server': 'http://localhost:8000/v1',  # api_base
+    'api_key': 'EMPTY',
+
+    # Other parameters:
+    # 'generate_cfg': {
+    #         # Add: When the response content is `<think>this is the thought</think>this is the answer;
+    #         # Do not add: When the response has been separated by reasoning_content and content.
+    #         'thought_in_content': True,
+    #     },
+}
+
+# Define Tools
+tools = [
+    {'mcpServers': {  # You can specify the MCP configuration file
+            'time': {
+                'command': 'uvx',
+                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
+            },
+        }
+    },
+  'code_interpreter',  # Built-in tools
+]
+
+# Define Agent
+bot = Assistant(llm=llm_cfg, function_list=tools)
+
+# Streaming generation
+messages = [{'role': 'user', 'content': 'What time is it?'}]
+for responses in bot.run(messages=messages):
+    pass
+print(responses)
+```
+
+## Processing Long Texts
+
+Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.
+
+YaRN is currently supported by several inference frameworks, e.g., `transformers` and `llama.cpp` for local use, `vllm` and `sglang` for deployment. In general, there are two approaches to enabling YaRN for supported frameworks:
+
+- Modifying the model files:
+  In the `config.json` file, add the `rope_scaling` fields:
+    ```json
+    {
+        ...,
+        "rope_scaling": {
+            "type": "yarn",
+            "factor": 4.0,
+            "original_max_position_embeddings": 32768
+        }
+    }
+    ```
+  For `llama.cpp`, you need to regenerate the GGUF file after the modification.
+
+- Passing command line arguments:
+
+  For `vllm`, you can use
+    ```shell
+    vllm serve ... --rope-scaling '{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072  
+    ```
+
+  For `sglang`, you can use
+    ```shell
+    python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}'
+    ```
+
+  For `llama-server` from `llama.cpp`, you can use
+    ```shell
+    llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768
+    ```
+
+> [!IMPORTANT]
+> If you encounter the following warning
+> ```
+> Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}
+> ```
+> please upgrade `transformers>=4.51.0`.
+
+> [!NOTE]
+> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
+> We advise adding the `rope_scaling` configuration only when processing long contexts is required. 
+> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0. 
+
+> [!NOTE]
+> The default `max_position_embeddings` in `config.json` is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance.
+
+> [!TIP]
+> The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.
+
+## Best Practices
+
+To achieve optimal performance, we recommend the following settings:
+
+1. **Sampling Parameters**:
+   - For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
+   - For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
+   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
+
+2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
+
+3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
+   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
+   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
+
+4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
+
+### Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3,
+    title  = {Qwen3},
+    url    = {https://qwenlm.github.io/blog/qwen3/},
+    author = {Qwen Team},
+    month  = {April},
+    year   = {2025}
+}
+```

text_encoder/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

text_encoder/chat_template.jinja

@@ -0,0 +1,97 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

text_encoder/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "model.layers.4.mlp",
+      "model.layers.6.self_attn",
+      "model.layers.34.self_attn",
+      "model.layers.33.self_attn",
+      "model.layers.4.self_attn",
+      "model.layers.34.mlp",
+      "model.layers.1.self_attn",
+      "model.layers.1.mlp",
+      "model.layers.0.mlp",
+      "model.layers.0.self_attn",
+      "model.layers.3.mlp",
+      "model.layers.6.mlp"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

text_encoder/configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

text_encoder/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 40960,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2059ddbe07963f57b58953c6c4799b53b544b05fa63b8306ec0818ce312a8c3
+size 3551775523

text_encoder/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

text_encoder/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

text_encoder/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- set message = messages[index] %}\n    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}\n    {%- set tool_start = '<tool_response>' %}\n    {%- set tool_start_length = tool_start|length %}\n    {%- set start_of_message = current_content[:tool_start_length] %}\n    {%- set tool_end = '</tool_response>' %}\n    {%- set tool_end_length = tool_end|length %}\n    {%- set start_pos = (current_content|length) - tool_end_length %}\n    {%- if start_pos < 0 %}\n        {%- set start_pos = 0 %}\n    {%- endif %}\n    {%- set end_of_message = current_content[start_pos:] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}\n        {%- set content = m_content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in m_content %}\n                {%- set content = (m_content.split('</think>')|last).lstrip('\\n') %}\n                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\\n') %}\n                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

tokenizer/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,46 @@
+{
+  "_class_name": "Flux2Transformer2DModel",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "/home/tonera/models/FLUX.2-klein-4B/transformer",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    32,
+    32,
+    32
+  ],
+  "eps": 1e-06,
+  "guidance_embeds": false,
+  "in_channels": 128,
+  "joint_attention_dim": 7680,
+  "mlp_ratio": 3.0,
+  "num_attention_heads": 24,
+  "num_layers": 5,
+  "num_single_layers": 20,
+  "out_channels": null,
+  "patch_size": 1,
+  "quantization_config": {
+    "modules_to_not_convert": null,
+    "quant_method": "torchao",
+    "quant_type": {
+      "default": {
+        "_data": {
+          "granularity": {
+            "_data": {
+              "dim": -1
+            },
+            "_type": "PerRow",
+            "_version": 1
+          },
+          "group_size": 64,
+          "set_inductor_config": true
+        },
+        "_type": "Int8WeightOnlyConfig",
+        "_version": 1
+      }
+    },
+    "quant_type_kwargs": {}
+  },
+  "rope_theta": 2000,
+  "timestep_guidance_channels": 256
+}

transformer/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b289352bf388995a2f0b9a38ec5032ddd57a937ff3e73ce6aa84e6caa4100ef
+size 4481249961

vae/config.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "AutoencoderKLFlux2",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "black-forest-labs/FLUX.2-dev",
+  "act_fn": "silu",
+  "batch_norm_eps": 0.0001,
+  "batch_norm_momentum": 0.1,
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 32,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "patch_size": [
+    2,
+    2
+  ],
+  "sample_size": 1024,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04
+size 168120878