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
+editing.jpg filter=lfs diff=lfs merge=lfs -text
+realism.jpg filter=lfs diff=lfs merge=lfs -text
+others.jpg filter=lfs diff=lfs merge=lfs -text
+flux2_klein.png filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+text_encoder/tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,53 @@
+FLUX Non-Commercial License v2.1
+
+Black Forest Labs Inc. (“we” or “our” or “Company”) is pleased to make the weights, parameters, and inference code for the FLUX Model (as defined below) freely available for your non-commercial and non-production use as set forth in this FLUX Non-Commercial License (“License”).  “FLUX Model” includes, individually and collectively, the models denoted as FLUX.x [dev], where “.x” denotes the FLUX Model version number, and models made available under the License, as indicated by a license notice that is included in or attached to the work, and their elements which includes algorithms, software, checkpoints, parameters, source code (inference code, evaluation code, and if applicable, fine-tuning code) and any other materials associated with the FLUX AI models made available by Company under this License, including if any, the technical documentation, manuals, and instructions for the use and operation thereof. Note that we may also make available certain elements of what is included in the definition of “FLUX Model” under a separate license, such as the inference code, and nothing in this License will be deemed to restrict or limit any other licenses granted by us in such elements.
+
+By downloading, accessing, using, Distributing (as defined below), or creating a Derivative (as defined below) of the FLUX Model, you agree to the terms of this License. If you do not agree to this License, then you do not have any rights to access, use, Distribute or create a Derivative of the FLUX Model and you must immediately cease using the FLUX Model. If you are agreeing to be bound by the terms of this License on behalf of your employer or other entity, you represent and warrant to us that you have full legal authority to bind your employer or such entity to this License. If you do not have the requisite authority, you may not accept the License or access the FLUX Model on behalf of your employer or other entity.
+
+ 1. Definitions.
+ - a. “Derivative”  means any (i) modified version of the FLUX Model (including but not limited to any customized or fine-tuned version thereof), (ii) work based on the FLUX Model, or (iii) any other derivative work thereof. For the avoidance of doubt, Outputs are not considered Derivatives under this License.
+ - b. “Distribution” or “Distribute” or “Distributing” means providing or making available, by any means, a copy of the FLUX Model and/or the Derivatives as the case may be.
+ - c. “Non-Commercial Purpose” means any of the following uses, but only so far as you do not receive any direct or indirect payment arising from the use of the FLUX Model, Derivatives, or Content Filters (as defined below): (i) personal use for research, experimentation, and testing for the benefit of public knowledge, personal study, private entertainment, hobby projects, or otherwise not directly or indirectly connected to any commercial activities, business operations, or employment responsibilities; (ii) use by commercial or for-profit entities for testing, evaluation, or non-commercial research and development in a non-production environment; and (iii) use by any charitable organization for charitable purposes, or for testing or evaluation. For clarity, use (a) for revenue-generating activity, (b) in direct interactions with or that has impact on end users, or (c) to train, fine tune, or distill other models for commercial use, in each case, is not a Non-Commercial Purpose.
+ - d. “Outputs” means any content generated by the operation of the FLUX Model or Derivatives from an input (such as an image input) or prompt (i.e., text instructions) provided by users. For the avoidance of doubt, Outputs do not include any components of the FLUX Model, such as any fine-tuned versions of the FLUX Model, the weights, or parameters.
+ - e.   “you” or “your” means the individual or entity entering into this License with Company.
+
+2. License Grant.
+- a. License. Subject to your compliance with this License, Company grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty free, and limited license to access, use, create Derivatives of, and Distribute the FLUX Model and Derivatives solely for your Non-Commercial Purposes. The foregoing license is personal to you, and you may not assign or sublicense this License or any other rights or obligations under this License without Company’s prior written consent; any such assignment or sublicense will be void and will automatically and immediately terminate this License.  Any restrictions set forth herein regarding the FLUX Model also apply to any Derivative you create or that are created on your behalf.
+- b. Non-Commercial Use Only.  You may only access, use, Distribute, or create Derivatives of the FLUX Model or Derivatives for Non-Commercial Purposes.  If you want to use a FLUX Model or a Derivative for any purpose that is not expressly authorized under this License, such as for a commercial activity, you must request a license from Company, which Company may grant to you in Company’s sole discretion and which additional use may be subject to a fee, royalty or other revenue share. Please see https://bfl.ai/licensing if you would like a commercial license.
+- c. Reserved Rights. The grant of rights expressly set forth in this License are the complete grant of rights to use the FLUX Model, and no other licenses are granted, whether by waiver, estoppel, implication, equity, or otherwise. Company and its licensors reserve all rights not expressly granted by this License.
+- d. Outputs. We claim no ownership rights in and to the Outputs. You are solely responsible for the Outputs you generate and their subsequent uses in accordance with this License. You may use Output for any purpose (including for commercial purposes), except as expressly prohibited herein. You may not use the Output to train, fine-tune, or distill a model that is competitive with a FLUX Model.
+- e. You may access, use, Distribute, or create Output of the FLUX Model or Derivatives if you: (i) (A) implement and maintain content filtering measures (“Content Filters”) for your use of the FLUX Model or Derivatives to prevent the creation, display, transmission, generation, or dissemination of unlawful or infringing content, which may include Content Filters that we may make available for use with the FLUX Model (“Provided Content Filters”), or (B) ensure Output undergoes review for unlawful or infringing content before public or non-public distribution, display, transmission or dissemination; and (ii) ensure Output includes disclosure (or other indication) that the Output was generated or modified using artificial intelligence technologies to the extent required under applicable law.
+
+3. Distribution. Subject to this License, you may Distribute copies of the FLUX Model and/or Derivatives made by you, under the following conditions:
+- a. you must make available a copy of this License to third-party recipients of the FLUX Mode and/or Derivatives you Distribute, and specify that any rights to use the FLUX Model and/or Derivatives shall be directly granted by Company to said third-party recipients pursuant to this License;
+- b. you must prominently display the following notice alongside the Distribution of the FLUX Model or Derivative (such as via a “Notice” text file distributed as part of such FLUX Model or Derivative) (the “Attribution Notice”):
+
+> This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Non-Commercial License. Copyright Black Forest Labs Inc. IN NO EVENT SHALL BLACK FOREST LABS INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
+
+- c. in the case of Distribution of Derivatives made by you: (i) you must also include in the Attribution Notice a statement that you have modified the applicable FLUX Model; (ii) any terms and conditions you impose on any third-party recipients relating to Derivatives made by or for you shall neither limit such third-party recipients’ use of the FLUX Model or any Derivatives made by or for Company in accordance with this License nor conflict with any of its terms and conditions and must include disclaimer of warranties and limitation of liability provisions that are at least as protective of Company as those set forth herein; and (iii) you must not misrepresent or imply, through any means, that the Derivatives made by or for you and/or any modified version of the FLUX Model you Distribute under your name and responsibility is an official product of the Company or has been endorsed, approved or validated by the Company, unless you are authorized by Company to do so in writing.
+
+4. Restrictions.  You will not, and will not permit, assist or cause any third party to
+- a. use, modify, copy, reproduce, create Derivatives of, or Distribute the FLUX Model (or any Derivative thereof, or any data produced by the FLUX Model), in whole or in part, (i) for any commercial or production purposes, (ii) military purposes, (iii) purposes of surveillance, including any research or development relating to surveillance, (iv) biometric processing, (v) in any manner that infringes, misappropriates, or otherwise violates (or is likely to infringe, misappropriate, or otherwise violate) any third party’s legal rights, including rights of publicity or “digital replica” rights, (vi) in any unlawful, fraudulent, defamatory, or abusive activity, (vii) to generate unlawful content, including child sexual abuse material, or non-consensual intimate images; or (viii) in any manner that violates any applicable law and any privacy or security laws, rules, regulations, directives, or governmental requirements (including the General Data Privacy Regulation (Regulation (EU) 2016/679), the California Consumer Privacy Act, any and all laws governing the processing of biometric information, and the EU Artificial Intelligence Act (Regulation (EU) 2024/1689), as well as all amendments and successor laws to any of the foregoing);
+  - b. alter or remove copyright and other proprietary notices which appear on or in any portion of the FLUX Model;
+  - c. utilize any equipment, device, software, or other means to circumvent or remove any security or protection used by Company in connection with the FLUX Model, or to circumvent or remove any usage restrictions, or to enable functionality disabled by FLUX  Model;
+  - d. offer or impose any terms on the FLUX Model that alter, restrict, or are inconsistent with the terms of this License;
+  - e. violate any applicable U.S. and non-U.S. export control and trade sanctions laws (“Export Laws”) in connection with your use or Distribution of any FLUX Model;
+  - f. directly or indirectly Distribute, export, or otherwise transfer FLUX Model (i) to any individual, entity, or country prohibited by Export Laws; (ii) to anyone on U.S. or non-U.S. government restricted parties lists; (iii) for any purpose prohibited by Export Laws, including nuclear, chemical or biological weapons, or missile technology applications; (iv) use or download FLUX Model if you or they are (a) located in a comprehensively sanctioned jurisdiction, (b) currently listed on any U.S. or non-U.S. restricted parties list, or (c) for any purpose prohibited by Export Laws; and (v) will not disguise your location through IP proxying or other methods.
+
+5. DISCLAIMERS.  THE FLUX MODEL AND PROVIDED CONTENT FILTERS ARE PROVIDED “AS IS” AND “WITH ALL FAULTS” WITH NO WARRANTY OF ANY KIND, EXPRESS OR IMPLIED. COMPANY EXPRESSLY DISCLAIMS ALL REPRESENTATIONS AND WARRANTIES, EXPRESS OR IMPLIED, WHETHER BY STATUTE, CUSTOM, USAGE OR OTHERWISE AS TO ANY MATTERS RELATED TO THE FLUX MODEL AND PROVIDED CONTENT FILTERS, INCLUDING BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, SATISFACTORY QUALITY, OR NON-INFRINGEMENT. COMPANY MAKES NO WARRANTIES OR REPRESENTATIONS THAT THE FLUX MODEL AND PROVIDED CONTENT FILTERS WILL BE ERROR FREE OR FREE OF VIRUSES OR OTHER HARMFUL COMPONENTS, OR PRODUCE ANY PARTICULAR RESULTS.
+
+6. LIMITATION OF LIABILITY.  TO THE FULLEST EXTENT PERMITTED BY LAW, IN NO EVENT WILL COMPANY BE LIABLE TO YOU OR YOUR EMPLOYEES, AFFILIATES, USERS, OFFICERS OR DIRECTORS (A) UNDER ANY THEORY OF LIABILITY, WHETHER BASED IN CONTRACT, TORT, NEGLIGENCE, STRICT LIABILITY, WARRANTY, OR OTHERWISE UNDER THIS LICENSE, OR (B) FOR ANY INDIRECT, CONSEQUENTIAL, EXEMPLARY, INCIDENTAL, PUNITIVE OR SPECIAL DAMAGES OR LOST PROFITS, EVEN IF COMPANY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. THE FLUX MODEL, ITS CONSTITUENT COMPONENTS, PROVIDED CONTENT FILTERS, AND ANY OUTPUT (COLLECTIVELY, “MODEL MATERIALS”) ARE NOT DESIGNED OR INTENDED FOR USE IN ANY APPLICATION OR SITUATION WHERE FAILURE OR FAULT OF THE MODEL MATERIALS COULD REASONABLY BE ANTICIPATED TO LEAD TO SERIOUS INJURY OF ANY PERSON, INCLUDING POTENTIAL DISCRIMINATION OR VIOLATION OF AN INDIVIDUAL’S PRIVACY RIGHTS, OR TO SEVERE PHYSICAL, PROPERTY, OR ENVIRONMENTAL DAMAGE (EACH, A “HIGH-RISK USE”). IF YOU ELECT TO USE ANY OF THE MODEL MATERIALS FOR A HIGH-RISK USE, YOU DO SO AT YOUR OWN RISK. YOU AGREE TO DESIGN AND IMPLEMENT APPROPRIATE DECISION-MAKING AND RISK-MITIGATION PROCEDURES AND POLICIES IN CONNECTION WITH A HIGH-RISK USE SUCH THAT EVEN IF THERE IS A FAILURE OR FAULT IN ANY OF THE MODEL MATERIALS, THE SAFETY OF PERSONS OR PROPERTY AFFECTED BY THE ACTIVITY STAYS AT A LEVEL THAT IS REASONABLE, APPROPRIATE, AND LAWFUL FOR THE FIELD OF THE HIGH-RISK USE.
+
+7. INDEMNIFICATION. You will indemnify, defend and hold harmless Company and our subsidiaries and affiliates, and each of our respective shareholders, directors, officers, employees, agents, successors, and assigns (collectively, the “Company Parties”) from and against any losses, liabilities, damages, fines, penalties, and expenses (including reasonable attorneys’ fees) incurred by any Company Party in connection with any claim, demand, allegation, lawsuit, proceeding, or investigation (collectively, “Claims”) arising out of or related to  (a) your access to or use of the FLUX Model (including in connection with any Output, results or data generated from such access or use, or from your access or use of any Content Filters), including any High-Risk Use; (b) your Content Filters, including your failure to implement any Content Filters where required by this License such as in Section 2(e); (c) your violation of this License; or (d) your violation, misappropriation or infringement of any rights of another (including intellectual property or other proprietary rights and privacy rights). You will promptly notify the Company Parties of any such Claims, and cooperate with Company Parties in defending such Claims. You will also grant the Company Parties sole control of the defense or settlement, at Company’s sole option, of any Claims. This indemnity is in addition to, and not in lieu of, any other indemnities or remedies set forth in a written agreement between you and Company or the other Company Parties.
+
+8. Termination; Survival.
+        a. This License will automatically terminate upon any breach by you of the terms of this License.
+        b. We may terminate this License, in whole or in part, at any time upon notice (including electronic) to you.
+        c. If you initiate any legal action or proceedings against Company or any other entity (including a cross-claim or counterclaim in a lawsuit), alleging that the FLUX Model, any Derivative, or Provided Content Filters, or any part thereof, infringe upon intellectual property or other rights owned or licensable by you, then any licenses granted to you under this License will immediately terminate as of the date such legal action or claim is filed or initiated.
+        d. Upon termination of this License, you must cease all use, access or Distribution of the FLUX Model, any Derivatives, and any Provided Content Filters.  The following sections survive termination of this License: 2(c), 2(d), 4-11.
+
+9. Third Party Materials. The FLUX Model and Provided Content Filters may contain third-party software or other components (including free and open source software) (all of the foregoing, “Third Party Materials”), which are subject to the license terms of the respective third-party licensors. Your dealings or correspondence with third parties and your use of or interaction with any Third Party Materials are solely between you and the third party. Company does not control or endorse, and makes no representations or warranties regarding, any Third Party Materials, and your access to and use of such Third Party Materials are at your own risk.
+
+10. Trademarks. You have not been granted any trademark license as part of this License and may not use any name, logo or trademark associated with Company without the prior written permission of Company, except to the extent necessary to make the reference required in the Attribution Notice as specified above or as is reasonably necessary in describing the FLUX Model and its creators.
+
+11. General. This License will be governed and construed under the laws of the State of Delaware without regard to conflicts of law provisions. If any provision or part of a provision of this License is unlawful, void or unenforceable, that provision or part of the provision is deemed severed from this License, and will not affect the validity and enforceability of any remaining provisions. The failure of Company to exercise or enforce any right or provision of this License will not operate as a waiver of such right or provision. This License does not confer any third-party beneficiary rights upon any other person or entity. This License, together with the documentation, contains the entire understanding between you and Company regarding the subject matter of this License, and supersedes all other written or oral agreements and understandings between you and Company regarding such subject matter.

README.md

@@ -1,3 +1,137 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+license: other
+license_name: flux-non-commercial-license
+extra_gated_prompt: >-
+  By clicking "Agree", you agree to the [FLUX Non-Commercial License
+  Agreement](LICENSE.md)
+  and acknowledge the [Acceptable Use
+  Policy](https://bfl.ai/legal/usage-policy).
+tags:
+- image-generation
+- image-editing
+- flux
+- diffusion-single-file
+pipeline_tag: image-to-image
+library_name: diffusers
+---
+
+![Teaser](./flux2_klein.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.
+
+FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.
+
+Our flagship small model. Defines the Pareto frontier for quality vs. latency across text-to-image, single-reference editing, and multi-reference generation. Matches or exceeds models 5x its size—in under half a second. Built on a 9B flow model with 8B Qwen3 text embedder, step-distilled to 4 inference steps.
+
+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 INT8 weight-only (int8wo) quantization, significantly reducing model size while maintaining generation quality.
+- **Text Encoder**: Replaced with `unsloth/Qwen3-8B-unsloth-bnb-4bit`, a 4-bit quantized version that further reduces memory requirements.
+- **Memory Usage**: Peak VRAM consumption is approximately **19GB**, making it accessible on NVIDIA RTX 3090 and above.
+- **Performance**: Generates images in approximately **4 seconds** (4 steps)on RTX 3090 GPUs.
+
+## **Using with Diffusers 🧨**
+
+To use FLUX.2 [klein] 9B 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-9B-Int8-TorchAo"
+prompt = "A cat holding a sign that says hello world"
+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
+
+**Original Model**: The FLUX.2 [klein] 9B model fits in ~29GB VRAM and is accessible on NVIDIA RTX 4090 and above.
+
+**Quantized Model (This Repository)**: This TorchAo quantized version requires approximately **19GB VRAM** and can run efficiently on NVIDIA RTX 3090 and above, generating images in about **4 seconds**.
+
+---
+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. Developers and users must consent to these conditions to access the FLUX.2 [klein] 9B models on Hugging Face.
+8. Safety. Black Forest Labs takes model safety seriously. We may monitor use to detect misuse or abuse of our models and services. 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 falls under the [FLUX Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.txt).
+
+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/.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1747252784

text_encoder/README.md

@@ -0,0 +1,344 @@
+---
+tags:
+- unsloth
+base_model:
+- Qwen/Qwen3-8B
+license: apache-2.0
+---
+# Qwen3-8B
+
+## 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
+
+**Qwen3-8B** has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Number of Parameters: 8.2B
+- Number of Paramaters (Non-Embedding): 6.95B
+- 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/Qwen3-8B"
+
+# 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/Qwen3-8B --enable-reasoning --reasoning-parser deepseek_r1
+    ```
+- SGLang:
+    ```shell
+    python -m sglang.launch_server --model-path Qwen/Qwen3-8B --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 for [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) and [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) users.
+
+### `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/Qwen3-8B"):
+        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
+from qwen_agent.agents import Assistant
+
+# Define LLM
+llm_cfg = {
+    'model': 'Qwen3-8B',
+
+    # 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']
+            },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
+        }
+    },
+  'code_interpreter',  # Built-in tools
+]
+
+# Define Agent
+bot = Assistant(llm=llm_cfg, function_list=tools)
+
+# Streaming generation
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
+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 +1,58 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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.34.self_attn",
+      "model.layers.34.mlp",
+      "model.layers.0.mlp",
+      "model.layers.1.mlp",
+      "model.layers.2.mlp",
+      "model.layers.4.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": false,
+  "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": "others", "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-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa07b1d85aaade0c3b2bbd7aa0ea0393047d0dd142c25e8f0dd050c9d38d38f
+size 4975369365

text_encoder/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b94de522205741bb172868995d13333dea9ada658915981154361314309af7b
+size 2504973894

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/aimodels/models/FLUX.2-klein-9B/transformer",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    32,
+    32,
+    32
+  ],
+  "eps": 1e-06,
+  "guidance_embeds": false,
+  "in_channels": 128,
+  "joint_attention_dim": 12288,
+  "mlp_ratio": 3.0,
+  "num_attention_heads": 32,
+  "num_layers": 8,
+  "num_single_layers": 24,
+  "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:d5693add2b499ae595c53efdf4255983b5b789b8111ce2aa3951f10f103ae7bd
+size 10497322109

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