Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+teaser.jpg filter=lfs diff=lfs merge=lfs -text
+base-example.png filter=lfs diff=lfs merge=lfs -text
+distilled-example.png filter=lfs diff=lfs merge=lfs -text
+launch-gallery.jpg filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,81 @@
+# FLUX Kommunity License v.1.0
+
+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 or commercial use as a Qualifying User as set forth in this FLUX Kommunity License (“License”).  “FLUX Model” includes, individually and collectively, the models denoted as “FLUX x”, where “x” denotes the FLUX Model version number, and 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, (iii) any other machine learning model created by transferring the patterns of the weights, parameters, operational patterns, or Output of the FLUX Model or any Derivative thereof to another model, such that the latter model exhibits behavior similar to FLUX Model or its Derivatives, including by distillation methods, methods using intermediate data representations, or methods based on training using synthetic-data Outputs generated by FLUX Model or Derivatives, or (iv) 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 (including but not limited to in a production environment), (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. “Output” means any result of operating or otherwise using the FLUX Model or Derivatives, including but not limited to images, audio, video, or action-prediction outputs. For the avoidance of doubt, Output does not include any components of the FLUX Model, including any fine-tuned versions of the FLUX Model, the weights, or parameters.
+
+e. “Qualifying User” means you, if at any time you together with your affiliates’ gross annualized revenue is less than US$5,000,000.
+
+f. “Robotics Uses” means any production robotic system, autonomous machine, embodied AI system, cyber-physical system, or other physical AI applications, including for the purpose of generating action-predictions, motion planning, or control signals for any physical device or equipment.
+
+g. “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: (i) your Non-Commercial Purposes, including non-commercial Robotics Uses; and (ii) solely if you are a Qualifying User, use Outputs, including Outputs from Derivatives, for commercial purposes, and you may access and use the FLUX Model and Derivatives in a production environment solely for the purpose of generating such Outputs, except as expressly prohibited herein. 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, except as set forth in Section 2.a.  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.
+
+e. You may access, use, Distribute, or create Output of the FLUX Model or Derivatives pursuant to Section 2.a as a Qualifying User 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, unsafe 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 disclosures (or other indications) 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 Model 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 Kommunity 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 (except as set forth in Section 2.a), (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, unsafe, 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. use the FLUX Model, any Derivatives, or any Output or results from the FLUX Model or Derivative to improve any other artificial intelligence model that performs any function similar to a FLUX Model or Derivative;
+
+c. alter or remove copyright and other proprietary notices which appear on or in any portion of the FLUX Model;
+
+d. 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;
+
+e. offer or impose any terms on the FLUX Model that alter, restrict, or are inconsistent with the terms of this License;
+
+f. 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;
+
+g. 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 (SUCH AS MACHINERY OR OTHER EQUIPMENT), 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.

NOTICE.md

@@ -0,0 +1 @@
+This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Kommunity 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.

README.md

@@ -0,0 +1,215 @@
+---
+language:
+- en
+license: other
+license_name: flux-kommunity-license
+license_link: LICENSE.md
+pipeline_tag: image-to-image
+library_name: diffusers
+tags:
+- image-generation
+- image-editing
+- flux
+- flux-3
+- black-forest-labs
+---
+
+# FLUX 3 Image Klein Base
+
+![Launch gallery](./launch-gallery.jpg)
+
+![Teaser](./teaser.jpg)
+
+FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder.
+
+The 5.6B parameter label refers to the image transformer; the text encoder is separate.
+
+This repository holds the undistilled base checkpoint, for fine-tuning, LoRA training and research. You can find the distilled checkpoint here: [FLUX 3 Image Klein](https://huggingface.co/black-forest-labs/flux-3-image-klein).
+
+Inference code, prompt upsampling and the bounding box format: [black-forest-labs/flux-3-image-klein](https://github.com/black-forest-labs/flux-3-image-klein) on GitHub.
+
+**Do not use the model without a prompt upsampler.** FLUX 3 Image Klein takes full scene captions, for text-to-image, editing and layout with boxes alike; a short prompt sent as typed gives generic output. Use ours, [flux-3-image-klein-pup](https://huggingface.co/black-forest-labs/flux-3-image-klein-pup), which the reference code loads by default, or any LLM you prefer with a system prompt that expands the request into one full scene caption ([`system_prompts.json`](https://huggingface.co/black-forest-labs/flux-3-image-klein-pup/blob/main/system_prompts.json) has ours). Diffusers runs neither on its own; see [Prompt upsampling](#prompt-upsampling).
+
+This repository includes the BF16 transformer and [FP8](https://huggingface.co/black-forest-labs/flux-3-image-klein-base/tree/main/variants/fp8r) and [NVFP4](https://huggingface.co/black-forest-labs/flux-3-image-klein-base/tree/main/variants/nvfp4) variants, together with the Qwen3-VL-4B-Instruct text encoder and image autoencoder.
+
+| Checkpoint | Format | Steps | Guidance | Built for |
+| --- | --- | --- | --- | --- |
+| [Klein Base](https://huggingface.co/black-forest-labs/flux-3-image-klein-base) | undistilled, bfloat16 | 50 | 3.5 | fine-tuning, LoRA training, research |
+| [Klein](https://huggingface.co/black-forest-labs/flux-3-image-klein) | distilled, bfloat16 | 16 | none | generation and editing, self-hosting; the checkpoint behind the BFL API |
+
+## Key Features
+
+1. Text-to-image, single-reference editing and multi-reference generation in one model.
+2. Bounding boxes in the prompt. Place elements with boxes on a 0 to 1000 grid, then recolor, move, replace or remove them through the prompt. Boxes guide placement and scale; they do not constrain pixels to a hard mask.
+3. Text rendering within generated images.
+4. Released under the [FLUX Kommunity License](LICENSE.md). The license permits non-commercial use and provides a commercial-output exception for Qualifying Users, subject to its terms. See [License](#license) below.
+
+## Download
+
+Download the root BF16 package and shared components without downloading the quantized variants:
+
+```python
+from huggingface_hub import snapshot_download
+
+snapshot_download(
+    repo_id="black-forest-labs/flux-3-image-klein-base",
+    local_dir="weights/flux-3-image-klein-base",
+    allow_patterns=[
+        "model.safetensors", "config.json", "manifest.json",
+        "ae.safetensors", "text_encoder/*",
+        "README.md", "LICENSE.md", "NOTICE.md",
+    ],
+)
+```
+
+To download a quantized transformer instead, replace the three root transformer patterns (`model.safetensors`, `config.json`, and `manifest.json`) with `variants/fp8r/*` or `variants/nvfp4/*`. Keep `ae.safetensors` and `text_encoder/*` for the shared components.
+
+These files contain the model package, not a complete inference application. Use an inference implementation that supports this checkpoint format. Quantized packages need a loader that supports their format; their file size is not a measure of total GPU memory use.
+
+## Using with reference code
+
+The distilled checkpoint is served on the [BFL API](https://bfl.ai) as FLUX 3 Image Klein. The reference inference code is [black-forest-labs/flux-3-image-klein](https://github.com/black-forest-labs/flux-3-image-klein).
+
+From the reference implementation checkout, install the package and download the two components the CLI loads besides this checkpoint. The CLI reads its weights from `weights/` (set `WEIGHTS_DIR` for another root), where the download above puts this repository.
+
+```bash
+pip install -e .
+
+# safety classifier, always loaded
+hf download Falconsai/nsfw_image_detection --local-dir weights/nsfw-classifier
+# prompt upsampler (18.8 GB), on by default; --no-pup sends the prompt as typed, for captions written by another LLM
+hf download black-forest-labs/flux-3-image-klein-pup --local-dir weights/pup
+
+# text-to-image
+python scripts/cli.py 'A chunky knitted diorama: three white cable-knit icebergs with tiny pale blue houses, a cream banner embroidered "KNITTED ICEBERG VILLAGE", a giant magenta knitted whale tail bursting from a yarn sea' \
+  --model base --out knitted.png
+
+# image editing; repeat --image for multiple references
+python scripts/cli.py 'the same scene at night under a knitted full moon, embroidered stars above the peaks' \
+  --model base --image knitted.png --out knitted_night.png
+```
+
+## Using with Diffusers
+
+FLUX 3 Image Klein uses a modular pipeline. Pass `prompt` for text-to-image generation, or pass `image` with a prompt for editing; `image` can be one image or a list of reference images. The model takes full scene captions, not short prompts: a request sent as typed gives generic output. Every request below goes through the [prompt upsampler](#prompt-upsampling) first, a separate 9B model ([black-forest-labs/flux-3-image-klein-pup](https://huggingface.co/black-forest-labs/flux-3-image-klein-pup)) that the pipeline does not run on its own. Load it beside the pipeline, then generate:
+
+```shell
+pip install git+https://github.com/huggingface/diffusers.git
+```
+
+```python
+import json
+
+import torch
+from diffusers import ModularPipeline
+from huggingface_hub import hf_hub_download
+from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
+
+pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base")
+pipe.load_components(dtype=torch.bfloat16)
+pipe.to("cuda")
+
+pup_id = "black-forest-labs/flux-3-image-klein-pup"
+processor = AutoProcessor.from_pretrained(pup_id)
+upsampler = Qwen3_5ForConditionalGeneration.from_pretrained(pup_id, dtype=torch.bfloat16, device_map="auto").eval()
+system_prompts = json.load(open(hf_hub_download(pup_id, "system_prompts.json")))
+
+
+def upsample(prompt, images=()):
+    if images:
+        text = (
+            "Reference images follow in order (the first image, the second image, ...).\n"
+            f"User request: {prompt}\nOutput the caption."
+        )
+        content = [{"type": "image", "image": image} for image in images] + [{"type": "text", "text": text}]
+        messages = [{"role": "system", "content": system_prompts["i2i"]}, {"role": "user", "content": content}]
+    else:
+        messages = [{"role": "system", "content": system_prompts["t2i"]}, {"role": "user", "content": prompt}]
+    inputs = processor.apply_chat_template(
+        messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", enable_thinking=False
+    ).to(upsampler.device)
+    with torch.no_grad():
+        output = upsampler.generate(**inputs, max_new_tokens=3584, do_sample=False)
+    return processor.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip()
+
+
+caption = upsample('A chunky knitted diorama: three white cable-knit icebergs with tiny pale blue houses, a cream banner embroidered "KNITTED ICEBERG VILLAGE", a giant magenta knitted whale tail bursting from a yarn sea')
+image = pipe(prompt=caption, generator=torch.Generator().manual_seed(1), output="images")[0]
+image.save("knitted.png")
+
+night = pipe(
+    prompt=upsample("the same scene at night under a knitted full moon, embroidered stars above the peaks", [image]),
+    image=image,
+    generator=torch.Generator().manual_seed(1),
+    output="images",
+)[0]
+night.save("knitted_night.png")
+```
+
+### Prompt upsampling
+
+The prompt upsampler turns a short request, together with the reference images when editing, into the full scene caption the model takes: medium and style, scene, lighting and camera, each subject with its colors, materials and position in the frame. The reference CLI runs it by default. `upsample` above runs it with Transformers: `system_prompts["t2i"]` for text-to-image, `system_prompts["i2i"]` with the references first in the user message for an edit, greedy decoding, thinking off. Its [model card](https://huggingface.co/black-forest-labs/flux-3-image-klein-pup) has the decoding settings and the layout form (`t2i_bbox`, `i2i_bbox`), which takes a list of boxes and writes the box table after the caption.
+
+Any other LLM can take its place: give it `system_prompts["t2i"]` (or `"i2i"` with the references) as the system prompt, the request as the user message, and pass the caption it returns as `prompt`.
+
+## Prompting
+The caption controls composition; reference images anchor content, they do not lock structure.
+- Always run a [prompt upsampler](#prompt-upsampling), ours or your own LLM: the model takes full scene captions (framing, subject, background, lighting), and a short prompt sent as typed gives generic output. A one-line edit instruction ("make it blue") reframes the shot.
+- For edits, the [prompt upsampler](#prompt-upsampling) writes the caption from the instruction and the references: a complete caption of the reference with the edit folded in. For style, describe the attributes (palette, stroke, texture) rather than naming an artwork.
+- For layout, append a JSON list of elements to the caption. Each box is `[top, left, bottom, right]` on a 0 to 1000 grid; tag the element in the caption with `<id>`:
+```text
+Minimalist graphic illustration featuring a black silhouette of a person <silhouette_1> centered against a solid, vibrant chartreuse background <background_1>. The figure is captured in a dynamic, mid-stride running pose, facing toward the left side of the frame. [{"id": "background_1", "bbox": [0, 0, 1000, 1000], "desc": "A flat field of neon yellow-green with a subtle paper texture and fine, organic grain."}, {"id": "silhouette_1", "bbox": [150, 150, 850, 850], "desc": "A black silhouette of a person in motion, made of dense stippled ink."}]
+```
+For edits by box, refer to the n-th reference as `<ref_image_n>` and give each element `from`, `src_bbox` and `tgt_bbox`; a `null` target removes it. The full format with worked examples: [Bounding boxes](https://docs.bfl.ai/flux_3/flux3_image_bounding_boxes).
+
+## Fine-tuning
+
+Train on this base checkpoint; it was trained without step or guidance distillation. The distilled checkpoint is intended for generation and editing rather than as the starting point for these training workflows.
+
+## 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. Short prompts produce generic output.
+- Boxes set placement and scale, not a hard mask: an element can extend past its box, and small requested elements may not appear. Edits can change content outside the requested region.
+
+## Hardware
+
+Peak GPU memory with the [reference code](https://github.com/black-forest-labs/flux-3-image-klein), B200, 1024x1024, prompt upsampler off: 31 GB in BF16, 29 GB in FP8, 26 GB in NVFP4. The prompt upsampler adds about 28 GB on an 80 GB GPU.
+
+## Out-of-scope use
+
+See Section 4 of the [FLUX Kommunity License](LICENSE.md) for the full restrictions. They include military purposes; surveillance, including related research and development; biometric processing; unlawful, unsafe, fraudulent, defamatory, or abusive activity; generating unlawful content, including child sexual abuse material or non-consensual intimate images; violating third-party rights, including rights of publicity or digital replica rights; and using the model, its Derivatives, or its Outputs to improve another AI model that performs a function similar to a FLUX Model or Derivative.
+
+The license also covers export controls and sanctions. Its commercial-use exception is not blanket permission for commercial fine-tuning or distribution. Consult the full license for the terms that apply to each use.
+
+Nothing contained in this model card should be interpreted as or deemed a restriction or modification to the license the model is released under.
+
+## Responsible AI Development
+
+Black Forest Labs is committed to responsible model development and deployment. Prior to releasing FLUX 3 Image Klein, we evaluated and mitigated a number of risks, including child sexual abuse material (CSAM) and nonconsensual intimate imagery (NCII). For detailed information about our mitigations, evaluation processes, content provenance features, and policies, please see our post: [Capable, Open, and Safe: Combating AI Misuse](https://bfl.ai/blog/capable-open-and-safe-combating-ai-misuse). 
+To report safety concerns, contact [safety@blackforestlabs.ai](mailto:safety@blackforestlabs.ai).
+
+## License
+
+This model is released under the [FLUX Kommunity License v.1.0](LICENSE.md): non-commercial use, plus commercial output generation by Qualifying Users with less than US$5M in gross annualized revenue, including affiliates, subject to the license terms. For other uses, see [commercial licensing](https://bfl.ai/licensing).
+
+The Qwen3-VL-4B-Instruct text encoder is under [Apache-2.0](text_encoder/LICENSE).
+
+## Trademarks and IP
+
+Use of Black Forest Labs and FLUX trademarks requires prior written permission, except for required attribution or necessary descriptive references. Use must not cause confusion or imply sponsorship or endorsement. Third-party trademarks remain subject to their owners' policies.
+
+## Citation
+
+If you use FLUX 3 Image in your work, please cite:
+
+```bibtex
+@misc{bfl2026flux3image,
+  author       = {{Black Forest Labs}},
+  title        = {{FLUX} 3 Image Klein},
+  year         = {2026},
+  url          = {https://bfl.ai/blog/flux-3-image-klein},
+}

ae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868fe7b343cc8f3a19dbcfcafbc3d5f888802be3f89bd81b65b3621a066ce8f3
+size 336211292

config.json

@@ -0,0 +1,37 @@
+{
+  "format_version": 1,
+  "model": "flux-3-image-klein",
+  "quantization": null,
+  "torch_dtype": "bfloat16",
+  "dit": {
+    "hidden": 3072,
+    "heads": 24,
+    "depth": 5,
+    "depth_single": 28,
+    "mlp_ratio": 3.0,
+    "axes_dim": [32, 32, 32, 32],
+    "theta": 10000,
+    "in_channels": {"image": 128, "image_cond": 128, "text": 20480},
+    "out_modes": ["image"],
+    "vec_in_dim": null,
+    "image_rope_scale": 0.5
+  },
+  "text_encoder": {
+    "path": "text_encoder",
+    "tokenizer": "text_encoder",
+    "layers": [4, 8, 12, 16, 20, 24, 28, 32],
+    "pad_multiple": 80,
+    "max_tokens": 8192,
+    "dtype": "bfloat16"
+  },
+  "vae": {
+    "path": "ae.safetensors",
+    "dtype": "float32"
+  },
+  "sampler": {
+    "steps": 50,
+    "guidance": 3.5,
+    "alpha": 6.93,
+    "size": [1024, 1024]
+  }
+}

manifest.json

@@ -0,0 +1,13 @@
+{
+  "format_version": 1,
+  "kind": "f3_dit_export",
+  "model": "flux-3-image-klein",
+  "source_dtype": "float32",
+  "dtype": "bfloat16",
+  "tensors": 357,
+  "params": 5538458368,
+  "validated_against": "exact key set and shapes of the previous flux-3-image-klein bf16 package (357 tensors)",
+  "sha256": {
+    "model.safetensors": "5c921759dc03663dbb67df11d8e3d317d2d5b893b31b969c95dc77ebf861b19c"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c921759dc03663dbb67df11d8e3d317d2d5b893b31b969c95dc77ebf861b19c
+size 11076957072

modular_model_index.json

@@ -0,0 +1,89 @@
+{
+  "_blocks_class_name": "Flux3AutoBlocks",
+  "_class_name": "Flux3ModularPipeline",
+  "_diffusers_version": "0.41.0.dev0",
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-base",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-base",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "Flux3Transformer2DModel",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-base",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "Flux3Transformer2DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLFlux2",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-base",
+      "revision": null,
+      "subfolder": "vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLFlux2"
+      ],
+      "variant": null
+    }
+  ],
+  "prompt_upsampler": [
+    "transformers",
+    "Qwen3_5ForConditionalGeneration",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-pup",
+      "revision": null,
+      "subfolder": "",
+      "type_hint": [
+        "transformers",
+        "Qwen3_5ForConditionalGeneration"
+      ],
+      "variant": null
+    }
+  ],
+  "prompt_upsampler_processor": [
+    "transformers",
+    "AutoProcessor",
+    {
+      "pretrained_model_name_or_path": "black-forest-labs/flux-3-image-klein-pup",
+      "revision": null,
+      "subfolder": "",
+      "type_hint": [
+        "transformers",
+        "AutoProcessor"
+      ],
+      "variant": null
+    }
+  ]
+}

text_encoder/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

text_encoder/README.md

@@ -0,0 +1,192 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
+---
+<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+
+# Qwen3-VL-4B-Instruct
+
+
+Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
+
+This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.
+
+Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.
+
+
+#### Key Enhancements:
+
+* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.
+
+* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos.
+
+* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.
+
+* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.
+
+* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers.
+
+* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.
+
+* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.
+
+* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension.
+
+
+#### Model Architecture Updates:
+
+<p align="center">
+    <img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_arc.jpg" width="80%"/>
+<p>
+
+
+1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
+
+2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
+
+3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.
+
+This is the weight repository for Qwen3-VL-4B-Instruct.
+
+
+---
+
+## Model Performance
+
+**Multimodal performance**
+
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_vl_instruct.jpg)
+
+**Pure text performance**
+![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_text_instruct.jpg)
+
+## Quickstart
+
+Below, we provide simple examples to show how to use Qwen3-VL with 🤖 ModelScope and 🤗 Transformers.
+
+The code of Qwen3-VL has been in the latest Hugging Face transformers and we advise you to build from source with command:
+```
+pip install git+https://github.com/huggingface/transformers
+# pip install transformers==4.57.0 # currently, V4.57.0 is not released
+```
+
+### Using 🤗 Transformers to Chat
+
+Here we show a code snippet to show how to use the chat model with `transformers`:
+
+```python
+from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
+
+# default: Load the model on the available device(s)
+model = Qwen3VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen3-VL-4B-Instruct", dtype="auto", device_map="auto"
+)
+
+# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
+# model = Qwen3VLForConditionalGeneration.from_pretrained(
+#     "Qwen/Qwen3-VL-4B-Instruct",
+#     dtype=torch.bfloat16,
+#     attn_implementation="flash_attention_2",
+#     device_map="auto",
+# )
+
+processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-4B-Instruct")
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt"
+)
+inputs = inputs.to(model.device)
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+### Generation Hyperparameters
+#### VL
+```bash
+export greedy='false'
+export top_p=0.8
+export top_k=20
+export temperature=0.7
+export repetition_penalty=1.0
+export presence_penalty=1.5
+export out_seq_length=16384
+```
+
+#### Text
+```bash
+export greedy='false'
+export top_p=1.0
+export top_k=40
+export repetition_penalty=1.0
+export presence_penalty=2.0
+export temperature=1.0
+export out_seq_length=32768
+```
+
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report}, 
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}, 
+}
+
+@article{Qwen2.5-VL,
+  title={Qwen2.5-VL Technical Report},
+  author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
+  journal={arXiv preprint arXiv:2502.13923},
+  year={2025}
+}
+
+@article{Qwen2VL,
+  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
+  author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
+  journal={arXiv preprint arXiv:2409.12191},
+  year={2024}
+}
+
+@article{Qwen-VL,
+  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
+  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
+  journal={arXiv preprint arXiv:2308.12966},
+  year={2023}
+}
+```

text_encoder/chat_template.json

@@ -0,0 +1,4 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\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' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.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        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\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{%- endif %}\n"
+}
+  

text_encoder/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/generation_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.8,
+    "repetition_penalty": 1.0,
+    "temperature": 0.7,
+    "transformers_version": "4.56.0"
+}

text_encoder/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a01a0556622645a3cce87b655bbbbbc1f170c196099f1b666c93202c3339a9
+size 4967229296

text_encoder/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046296a2a387efb43b0c997d5833c789604d168834f6e0d3064bf7bb13d002a6
+size 3908490048

text_encoder/model.safetensors.index.json

@@ -0,0 +1,720 @@
+{
+  "metadata": {
+    "total_size": 8875631616
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
+  }
+}

text_encoder/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

text_encoder/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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\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' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.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        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

text_encoder/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

transformer/config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "Flux3Transformer2DModel",
+  "_diffusers_version": "0.41.0.dev0",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    32,
+    32,
+    32
+  ],
+  "cond_in_channels": 128,
+  "eps": 1e-06,
+  "in_channels": 128,
+  "joint_attention_dim": 20480,
+  "mlp_ratio": 3.0,
+  "num_attention_heads": 24,
+  "num_layers": 5,
+  "num_single_layers": 28,
+  "rope_theta": 10000,
+  "timestep_channels": 256
+}

transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160026c6235e6a10842208d4f4077fd51018cdc525b57e69385a783d7a4d4b43
+size 9887081880

transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4a893a94561112c9cfc2d69f4043d6686e012b050a9c7149d064e23d92413a
+size 1189878064

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,364 @@
+{
+  "metadata": {
+    "total_size": 11076916736
+  },
+  "weight_map": {
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "early_stream_modulations.image.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "early_stream_modulations.image_cond.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "early_stream_modulations.txt.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "mode_blocks.image_cond.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_stream_modulations.image.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_stream_modulations.image_cond.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_stream_modulations.txt.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.11.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.12.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.13.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.14.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.15.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.16.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.17.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.18.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.19.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.20.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.21.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.22.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.23.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.23.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.24.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.25.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.26.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.27.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "txt_mode_blocks.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_embedders.image.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_embedders.image_cond.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "AutoencoderKLFlux2",
+  "_diffusers_version": "0.41.0.dev0",
+  "act_fn": "silu",
+  "batch_norm_eps": 0.0001,
+  "batch_norm_momentum": 0.1,
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "decoder_block_out_channels": null,
+  "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:d64f3a68e1cc4f9f4e29b6e0da38a0204fe9a49f2d4053f0ec1fa1ca02f9c4b5
+size 336213556

variants/fp8r/config.json

@@ -0,0 +1,37 @@
+{
+  "format_version": 1,
+  "model": "flux-3-image-klein",
+  "quantization": "fp8r",
+  "torch_dtype": "bfloat16",
+  "dit": {
+    "hidden": 3072,
+    "heads": 24,
+    "depth": 5,
+    "depth_single": 28,
+    "mlp_ratio": 3.0,
+    "axes_dim": [32, 32, 32, 32],
+    "theta": 10000,
+    "in_channels": {"image": 128, "image_cond": 128, "text": 20480},
+    "out_modes": ["image"],
+    "vec_in_dim": null,
+    "image_rope_scale": 0.5
+  },
+  "text_encoder": {
+    "path": "text_encoder",
+    "tokenizer": "text_encoder",
+    "layers": [4, 8, 12, 16, 20, 24, 28, 32],
+    "pad_multiple": 80,
+    "max_tokens": 8192,
+    "dtype": "bfloat16"
+  },
+  "vae": {
+    "path": "ae.safetensors",
+    "dtype": "float32"
+  },
+  "sampler": {
+    "steps": 50,
+    "guidance": 3.5,
+    "alpha": 6.93,
+    "size": [1024, 1024]
+  }
+}

variants/fp8r/hf_quant_config.json

@@ -0,0 +1,47 @@
+{
+  "producer": {
+    "name": "bfl"
+  },
+  "quantization": {
+    "quant_algo": "FP8_PER_CHANNEL_PER_TOKEN",
+    "exclude_modules": [
+      "emb_in.image",
+      "emb_in.image_cond",
+      "final_layer.image.adaLN_modulation.1",
+      "final_layer.image.linear",
+      "time_in.in_layer",
+      "time_in.out_layer",
+      "txt_in",
+      "txt_mode_blocks.0.attn_out",
+      "txt_mode_blocks.0.k_proj",
+      "txt_mode_blocks.0.mlp_in",
+      "txt_mode_blocks.0.mlp_out",
+      "txt_mode_blocks.0.q_proj",
+      "txt_mode_blocks.0.v_proj",
+      "txt_mode_blocks.1.attn_out",
+      "txt_mode_blocks.1.k_proj",
+      "txt_mode_blocks.1.mlp_in",
+      "txt_mode_blocks.1.mlp_out",
+      "txt_mode_blocks.1.q_proj",
+      "txt_mode_blocks.1.v_proj",
+      "txt_mode_blocks.2.attn_out",
+      "txt_mode_blocks.2.k_proj",
+      "txt_mode_blocks.2.mlp_in",
+      "txt_mode_blocks.2.mlp_out",
+      "txt_mode_blocks.2.q_proj",
+      "txt_mode_blocks.2.v_proj",
+      "txt_mode_blocks.3.attn_out",
+      "txt_mode_blocks.3.k_proj",
+      "txt_mode_blocks.3.mlp_in",
+      "txt_mode_blocks.3.mlp_out",
+      "txt_mode_blocks.3.q_proj",
+      "txt_mode_blocks.3.v_proj",
+      "txt_mode_blocks.4.attn_out",
+      "txt_mode_blocks.4.k_proj",
+      "txt_mode_blocks.4.mlp_in",
+      "txt_mode_blocks.4.mlp_out",
+      "txt_mode_blocks.4.q_proj",
+      "txt_mode_blocks.4.v_proj"
+    ]
+  }
+}

variants/fp8r/manifest.json

@@ -0,0 +1,58 @@
+{
+  "format_version": 1,
+  "kind": "f3_dit_export",
+  "model": "flux-3-image-klein",
+  "quantization": "fp8r",
+  "dtype": "float8_e4m3fn",
+  "source_dtype": "bfloat16",
+  "scale_convention": "weight.float() * weight_scale[:, None]",
+  "tensors": 591,
+  "fp8_matrices": 234,
+  "weight_scales": 234,
+  "bf16_matrices": 37,
+  "bf16_tensors": 86,
+  "exclude_modules": [
+    "emb_in.image",
+    "emb_in.image_cond",
+    "final_layer.image.adaLN_modulation.1",
+    "final_layer.image.linear",
+    "time_in.in_layer",
+    "time_in.out_layer",
+    "txt_in",
+    "txt_mode_blocks.0.attn_out",
+    "txt_mode_blocks.0.k_proj",
+    "txt_mode_blocks.0.mlp_in",
+    "txt_mode_blocks.0.mlp_out",
+    "txt_mode_blocks.0.q_proj",
+    "txt_mode_blocks.0.v_proj",
+    "txt_mode_blocks.1.attn_out",
+    "txt_mode_blocks.1.k_proj",
+    "txt_mode_blocks.1.mlp_in",
+    "txt_mode_blocks.1.mlp_out",
+    "txt_mode_blocks.1.q_proj",
+    "txt_mode_blocks.1.v_proj",
+    "txt_mode_blocks.2.attn_out",
+    "txt_mode_blocks.2.k_proj",
+    "txt_mode_blocks.2.mlp_in",
+    "txt_mode_blocks.2.mlp_out",
+    "txt_mode_blocks.2.q_proj",
+    "txt_mode_blocks.2.v_proj",
+    "txt_mode_blocks.3.attn_out",
+    "txt_mode_blocks.3.k_proj",
+    "txt_mode_blocks.3.mlp_in",
+    "txt_mode_blocks.3.mlp_out",
+    "txt_mode_blocks.3.q_proj",
+    "txt_mode_blocks.3.v_proj",
+    "txt_mode_blocks.4.attn_out",
+    "txt_mode_blocks.4.k_proj",
+    "txt_mode_blocks.4.mlp_in",
+    "txt_mode_blocks.4.mlp_out",
+    "txt_mode_blocks.4.q_proj",
+    "txt_mode_blocks.4.v_proj"
+  ],
+  "source_sha256": "5c921759dc03663dbb67df11d8e3d317d2d5b893b31b969c95dc77ebf861b19c",
+  "sha256": {
+    "config.json": "09eca89ea7721ce2002c39be0e2ac57000894536b046f1bf7fd794e0945a5356",
+    "model.safetensors": "60de5b577f26b6bc3cf4823c180406f888416caec9474265c82d71cc4b515241"
+  }
+}

variants/fp8r/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60de5b577f26b6bc3cf4823c180406f888416caec9474265c82d71cc4b515241
+size 6250501712

variants/nvfp4/config.json

@@ -0,0 +1,37 @@
+{
+  "format_version": 1,
+  "model": "flux-3-image-klein",
+  "quantization": "nvfp4",
+  "torch_dtype": "bfloat16",
+  "dit": {
+    "hidden": 3072,
+    "heads": 24,
+    "depth": 5,
+    "depth_single": 28,
+    "mlp_ratio": 3.0,
+    "axes_dim": [32, 32, 32, 32],
+    "theta": 10000,
+    "in_channels": {"image": 128, "image_cond": 128, "text": 20480},
+    "out_modes": ["image"],
+    "vec_in_dim": null,
+    "image_rope_scale": 0.5
+  },
+  "text_encoder": {
+    "path": "text_encoder",
+    "tokenizer": "text_encoder",
+    "layers": [4, 8, 12, 16, 20, 24, 28, 32],
+    "pad_multiple": 80,
+    "max_tokens": 8192,
+    "dtype": "bfloat16"
+  },
+  "vae": {
+    "path": "ae.safetensors",
+    "dtype": "float32"
+  },
+  "sampler": {
+    "steps": 50,
+    "guidance": 3.5,
+    "alpha": 6.93,
+    "size": [1024, 1024]
+  }
+}

variants/nvfp4/hf_quant_config.json

@@ -0,0 +1,84 @@
+{
+  "producer": {
+    "name": "bfl"
+  },
+  "quantization": {
+    "quant_algo": "NVFP4",
+    "group_size": 16,
+    "exclude_modules": [
+      "content_mode_blocks.image.0.attn_out",
+      "content_mode_blocks.image.0.k_proj",
+      "content_mode_blocks.image.0.mlp_in",
+      "content_mode_blocks.image.0.mlp_out",
+      "content_mode_blocks.image.0.q_proj",
+      "content_mode_blocks.image.0.v_proj",
+      "early_stream_modulations.image.lin",
+      "early_stream_modulations.image_cond.lin",
+      "early_stream_modulations.txt.lin",
+      "emb_in.image",
+      "emb_in.image_cond",
+      "final_layer.image.adaLN_modulation.1",
+      "final_layer.image.linear",
+      "single_blocks.24.attn_out",
+      "single_blocks.24.k_proj",
+      "single_blocks.24.mlp_in",
+      "single_blocks.24.mlp_out",
+      "single_blocks.24.q_proj",
+      "single_blocks.24.v_proj",
+      "single_blocks.25.attn_out",
+      "single_blocks.25.k_proj",
+      "single_blocks.25.mlp_in",
+      "single_blocks.25.mlp_out",
+      "single_blocks.25.q_proj",
+      "single_blocks.25.v_proj",
+      "single_blocks.26.attn_out",
+      "single_blocks.26.k_proj",
+      "single_blocks.26.mlp_in",
+      "single_blocks.26.mlp_out",
+      "single_blocks.26.q_proj",
+      "single_blocks.26.v_proj",
+      "single_blocks.27.attn_out",
+      "single_blocks.27.k_proj",
+      "single_blocks.27.mlp_in",
+      "single_blocks.27.mlp_out",
+      "single_blocks.27.q_proj",
+      "single_blocks.27.v_proj",
+      "single_stream_modulations.image.lin",
+      "single_stream_modulations.image_cond.lin",
+      "single_stream_modulations.txt.lin",
+      "time_in.in_layer",
+      "time_in.out_layer",
+      "txt_in",
+      "txt_mode_blocks.0.attn_out",
+      "txt_mode_blocks.0.k_proj",
+      "txt_mode_blocks.0.mlp_in",
+      "txt_mode_blocks.0.mlp_out",
+      "txt_mode_blocks.0.q_proj",
+      "txt_mode_blocks.0.v_proj",
+      "txt_mode_blocks.1.attn_out",
+      "txt_mode_blocks.1.k_proj",
+      "txt_mode_blocks.1.mlp_in",
+      "txt_mode_blocks.1.mlp_out",
+      "txt_mode_blocks.1.q_proj",
+      "txt_mode_blocks.1.v_proj",
+      "txt_mode_blocks.2.attn_out",
+      "txt_mode_blocks.2.k_proj",
+      "txt_mode_blocks.2.mlp_in",
+      "txt_mode_blocks.2.mlp_out",
+      "txt_mode_blocks.2.q_proj",
+      "txt_mode_blocks.2.v_proj",
+      "txt_mode_blocks.3.attn_out",
+      "txt_mode_blocks.3.k_proj",
+      "txt_mode_blocks.3.mlp_in",
+      "txt_mode_blocks.3.mlp_out",
+      "txt_mode_blocks.3.q_proj",
+      "txt_mode_blocks.3.v_proj",
+      "txt_mode_blocks.4.attn_out",
+      "txt_mode_blocks.4.k_proj",
+      "txt_mode_blocks.4.mlp_in",
+      "txt_mode_blocks.4.mlp_out",
+      "txt_mode_blocks.4.q_proj",
+      "txt_mode_blocks.4.v_proj"
+    ]
+  }
+}

variants/nvfp4/manifest.json

@@ -0,0 +1,117 @@
+{
+  "format_version": 1,
+  "kind": "f3_dit_export",
+  "model": "flux-3-image-klein",
+  "quantization": "nvfp4",
+  "dtype": "nvfp4: weight uint8 [N, K/2] packed e2m1 (even element in low nibble), weight_scale float8_e4m3fn [N, K/16] row-major (not swizzled), weight_scale_2 and input_scale float32 scalars",
+  "source_dtype": "bfloat16",
+  "group_size": 16,
+  "scale_convention": "e2m1(weight) * weight_scale[:, k // 16] * weight_scale_2; weight_scale_2 = amax(weight) / (448 * 6); weight_scale = the positive finite e4m3 code minimizing the block's squared error; input_scale = p99.9 of per-call input amax / (448 * 6)",
+  "weight_scales": {
+    "method": "mse_fp8_scale_sweep",
+    "candidates": 126
+  },
+  "tensors": 951,
+  "nvfp4_matrices": 198,
+  "weight_scale_tensors": 198,
+  "weight_scale_2": 198,
+  "input_scales": 198,
+  "bf16_matrices": 73,
+  "bf16_tensors": 86,
+  "exclude_modules": [
+    "content_mode_blocks.image.0.attn_out",
+    "content_mode_blocks.image.0.k_proj",
+    "content_mode_blocks.image.0.mlp_in",
+    "content_mode_blocks.image.0.mlp_out",
+    "content_mode_blocks.image.0.q_proj",
+    "content_mode_blocks.image.0.v_proj",
+    "early_stream_modulations.image.lin",
+    "early_stream_modulations.image_cond.lin",
+    "early_stream_modulations.txt.lin",
+    "emb_in.image",
+    "emb_in.image_cond",
+    "final_layer.image.adaLN_modulation.1",
+    "final_layer.image.linear",
+    "single_blocks.24.attn_out",
+    "single_blocks.24.k_proj",
+    "single_blocks.24.mlp_in",
+    "single_blocks.24.mlp_out",
+    "single_blocks.24.q_proj",
+    "single_blocks.24.v_proj",
+    "single_blocks.25.attn_out",
+    "single_blocks.25.k_proj",
+    "single_blocks.25.mlp_in",
+    "single_blocks.25.mlp_out",
+    "single_blocks.25.q_proj",
+    "single_blocks.25.v_proj",
+    "single_blocks.26.attn_out",
+    "single_blocks.26.k_proj",
+    "single_blocks.26.mlp_in",
+    "single_blocks.26.mlp_out",
+    "single_blocks.26.q_proj",
+    "single_blocks.26.v_proj",
+    "single_blocks.27.attn_out",
+    "single_blocks.27.k_proj",
+    "single_blocks.27.mlp_in",
+    "single_blocks.27.mlp_out",
+    "single_blocks.27.q_proj",
+    "single_blocks.27.v_proj",
+    "single_stream_modulations.image.lin",
+    "single_stream_modulations.image_cond.lin",
+    "single_stream_modulations.txt.lin",
+    "time_in.in_layer",
+    "time_in.out_layer",
+    "txt_in",
+    "txt_mode_blocks.0.attn_out",
+    "txt_mode_blocks.0.k_proj",
+    "txt_mode_blocks.0.mlp_in",
+    "txt_mode_blocks.0.mlp_out",
+    "txt_mode_blocks.0.q_proj",
+    "txt_mode_blocks.0.v_proj",
+    "txt_mode_blocks.1.attn_out",
+    "txt_mode_blocks.1.k_proj",
+    "txt_mode_blocks.1.mlp_in",
+    "txt_mode_blocks.1.mlp_out",
+    "txt_mode_blocks.1.q_proj",
+    "txt_mode_blocks.1.v_proj",
+    "txt_mode_blocks.2.attn_out",
+    "txt_mode_blocks.2.k_proj",
+    "txt_mode_blocks.2.mlp_in",
+    "txt_mode_blocks.2.mlp_out",
+    "txt_mode_blocks.2.q_proj",
+    "txt_mode_blocks.2.v_proj",
+    "txt_mode_blocks.3.attn_out",
+    "txt_mode_blocks.3.k_proj",
+    "txt_mode_blocks.3.mlp_in",
+    "txt_mode_blocks.3.mlp_out",
+    "txt_mode_blocks.3.q_proj",
+    "txt_mode_blocks.3.v_proj",
+    "txt_mode_blocks.4.attn_out",
+    "txt_mode_blocks.4.k_proj",
+    "txt_mode_blocks.4.mlp_in",
+    "txt_mode_blocks.4.mlp_out",
+    "txt_mode_blocks.4.q_proj",
+    "txt_mode_blocks.4.v_proj"
+  ],
+  "calibration": {
+    "method": "p99.9 of per-call amax",
+    "prompts": 37,
+    "images": 37,
+    "images_t2i": 31,
+    "images_i2i": 6,
+    "steps": 50,
+    "guidance": 3.5,
+    "resolutions": [
+      "1024x1024",
+      "1152x896",
+      "1344x768",
+      "768x1344",
+      "912x1152"
+    ]
+  },
+  "source_sha256": "5c921759dc03663dbb67df11d8e3d317d2d5b893b31b969c95dc77ebf861b19c",
+  "sha256": {
+    "config.json": "b220b36d76f4d9c32cb016d528681a63f7582933114215643988b8a703e61ab6",
+    "model.safetensors": "fa3341c15644cbcbae9416c40349b82d8dc20bdd9224a64f4d63818b1116df3e"
+  }
+}

variants/nvfp4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3341c15644cbcbae9416c40349b82d8dc20bdd9224a64f4d63818b1116df3e
+size 5257226696