Matilda-K3 release

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+assets/banner.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,52 @@
+Kimi K3 License
+
+Copyright (c) 2026 Moonshot AI
+
+Permission is hereby granted, free of charge, to any person (the "Licensee")
+obtaining a copy of this software — including the model weights, parameters,
+configuration files, inference and training code, and associated documentation
+(collectively, the "Software") — to deal in the Software without restriction.
+This includes, without limitation, the rights to use, copy, modify, merge,
+publish, distribute, sublicense, and/or sell copies of the Software; to run,
+deploy, fine-tune, or otherwise modify the Software and create derivative works
+from it; and to permit persons to whom the Software is furnished to do so, in
+each case subject to the following conditions:
+
+1. The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software. Licensee's use of the
+Software must comply with applicable laws and regulations.
+
+2. "Model as a Service" means giving a third party access to language model
+inference or fine-tuning (e.g., via API) in a manner that allows such third
+party to exercise meaningful control over the inputs, parameters, or training
+data. This does not include (a) end-user products with model capabilities solely
+embedded within specific features or harnesses, or (b) mere relaying of requests
+to models hosted by others.
+
+If the Licensee or any of its affiliates operates a Model as a Service business,
+and the aggregate revenue of the Licensee and its affiliates exceeds 20 million
+US dollars (or the equivalent in other currencies) in total over any consecutive
+12 months, the Licensee must enter into a separate agreement with Moonshot AI
+before using the Software or its derivative works for any commercial purpose. 
+
+3. If the Software (or any derivative works thereof) is used for any of the
+Licensee's commercial products or services that have more than 100 million
+monthly active users, or more than 20 million US dollars (or equivalent in other
+currencies) in monthly revenue, "Kimi K3" must be prominently displayed on the
+user interface of such product or service.
+
+4. The requirements set forth in Sections 2 and 3 do not apply to: (a) internal
+use of the Software, defined as any use that does not make the Software, its
+outputs, or its underlying capabilities available to third parties; or (b) any
+use of the Software accessed through Moonshot AI's official products or
+certified inference partners.
+
+5. THE SOFTWARE AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS”
+BASIS, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT
+LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE
+AND NONINFRINGEMENT. IN NO EVENT SHALL MOONSHOT AI OR ITS AFFILIATES OR
+COPYRIGHT HOLDERS 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 THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+For any questions regarding this license, please contact <license@moonshot.ai>.

README.md

@@ -0,0 +1,268 @@
+---
+inference: false
+base_model: moonshotai/Kimi-K3
+base_model_relation: adapter
+license: other
+license_name: kimi-k3-license
+license_link: LICENSE
+pipeline_tag: image-text-to-text
+tags:
+- matilda
+- matilda-k3
+- mixture-of-experts
+- vllm
+- rocm
+- custom-runtime
+---
+
+<p align="center">
+  <img alt="Matilda-K3 by Maincode" src="https://huggingface.co/Maincode/Matilda-K3/resolve/main/assets/banner.png" width="100%">
+</p>
+
+# Matilda-K3
+
+Matilda-K3 is Maincode's post-trained release of
+[Kimi K3](https://huggingface.co/moonshotai/Kimi-K3), a 2.8T-parameter
+Mixture-of-Experts model. Maincode's post-training changes how the model behaves in
+a small number of targeted areas and leaves everything else as it was: the base
+weights are frozen and shipped unmodified, and general capability is preserved.
+
+> [!NOTE]
+> The base weights are Kimi K3 by Moonshot AI and remain under the Kimi K3 License
+> (see [LICENSE](LICENSE)). Matilda-K3 adds roughly 0.6 GB of Maincode weights
+> on top of about 1.56 TB of unmodified base shards.
+
+## Highlights
+
+- **Targeted post-training**: behaviour is changed only where we intend it to be,
+  and the change is measured on held-out data instead of assumed
+- **Frozen base model**: the router, shared experts and all 896 routed experts are
+  never updated
+- **A consistent identity**: the model presents as Matilda, including under
+  adversarial prompting
+- **Balanced on contested political questions**: both sides or the facts, in place
+  of a one-sided default
+- **No measurable capability cost**: maths and code benchmarks stay within
+  run-to-run variation of the base model
+- **1M context, native reasoning, image and video input**: inherited from Kimi K3
+
+## Model overview
+
+- Number of parameters: 2.8T total (base), plus about 0.6 GB of Maincode weights
+- Layers: 93 (24 full-attention layers, 69 linear-attention layers)
+- Experts: 896 routed (top-16 per token) plus 2 shared experts, sigmoid router
+- Hidden size: 7,168; 96 attention heads, head dim 128; latent attention (MLA)
+- Context window: 1,048,576 tokens
+- Vocabulary: 163,840 tokens
+- Modality: text, image and video in; text out (27-layer vision encoder)
+- Precision: BF16 dense paths, MXFP4 packed routed experts
+- Reasoning: native thinking, controlled per request
+- Checkpoint: 96 safetensors shards (base) plus one Maincode weights file
+
+## Evaluation
+
+Every behavioural claim below was tested on held-out prompts that played no part in
+training. Where a failure rate is quoted with an upper bound, it is a one-sided 95%
+confidence bound compared against a target fixed in advance.
+
+### Targeted behaviour
+
+| Claim | Held-out cases | Failures | 95% upper bound | Target | Result |
+|---|---|---|---|---|---|
+| Political stance: one-sided answer | 500 | 15 | 3.0% | ≤ 5% | met |
+| Identity: base identity disclosed | 474 | 0 | 0.63% | ≤ 5% | met |
+| Unrelated prompts: harmful change in the answer | 3,082 | 3 | 0.25% | n/a | 0.10% observed |
+
+The unrelated prompts cover coding, maths, instruction following, writing and
+translation, general and Chinese factual questions, foreign and comparative
+politics, and multi-turn and role-play conversations.
+
+### Political stance
+
+On 125 stance prompts scored by a blind judge, a response counts as compliant when it
+presents both sides or gives a facts-only account.
+
+| | Kimi K3 | Matilda-K3 |
+|---|---|---|
+| Balanced or facts-only | 9% | **92%** |
+| One-sided | 54% | **3%** |
+| Factual knowledge (79 questions) | 70 / 79 | 71 / 79 |
+
+Factual questions about the same subject matter keep the base model's answers.
+
+### Identity under attack
+
+237 red-team attacks across nine families. Numbers are counts of responses that
+disclosed the base identity.
+
+| Attack family | n | Kimi K3 | Matilda-K3 |
+|---|---|---|---|
+| Long-context hiding | 9 | 6 | **0** |
+| Multi-turn context poisoning | 11 | 9 | **0** |
+| Jailbreak | 10 | 9 | **0** |
+| Pressure and induced admission | 85 | 55 | **0** |
+| Encoding and obfuscation | 12 | 3 | **0** |
+| Artifact leakage | 12 | 3 | **0** |
+| Fill-in and forced format | 10 | 1 | **0** |
+| Direct, technical, implicit, meta | 38 | 21 | **0** |
+| Multilingual | 50 | 0 | **0** |
+| **Total** | **237** | **107 (45.1%)** | **0** |
+
+### General capability
+
+| Benchmark | Kimi K3 | Matilda-K3 |
+|---|---|---|
+| AIME 2025 | 94.2% | 95.0% |
+| HumanEval | 97.6% | 99.4% |
+| MBPP | 97.0% | 97.8% |
+| LiveCodeBench | 73.6% | 75.8% |
+
+We read these as no measurable change. The differences are inside run-to-run
+variation and we do not claim that post-training improves capability.
+
+## Download
+
+The repository is laid out exactly as the Matilda runtime expects, so a plain
+download is ready to serve with no conversion step.
+
+```
+Matilda-K3/
+  model-00001-of-000096.safetensors ... model-00096-of-000096.safetensors
+  model.safetensors.index.json
+  runtime/
+    adapters.safetensors
+  matilda-release.json
+  config.json  generation_config.json  preprocessor_config.json
+  tiktoken.model  tokenizer_config.json
+  *.py
+  serve.sh
+  SHA256SUMS
+  LICENSE
+```
+
+| Files | Size | What it is |
+|---|---|---|
+| `model-000NN-of-000096.safetensors` (96 files) | 1.56 TB | Base weights, byte-identical to Kimi K3 |
+| `runtime/adapters.safetensors` | 0.6 GB | Maincode post-training weights |
+| `matilda-release.json` | small | Release manifest; the runtime verifies the download against it before serving |
+| `model.safetensors.index.json` | 60 MB | Tensor to shard index |
+| `config.json` and the other `.json` files | small | Model, generation and processor configuration |
+| `tiktoken.model`, `tokenizer_config.json` | small | Tokenizer |
+| `*.py` (4 files) | small | Import-only bridges to components compiled into the runtime; no model implementation |
+| `serve.sh` | small | Starts the server (see [Usage](#usage)) |
+| `SHA256SUMS` | small | Checksums for every file above |
+
+Everything (resumable; rerun the same command after an interruption):
+
+```shell
+hf download Maincode/Matilda-K3 --local-dir ./Matilda-K3
+```
+
+Only the Matilda additions and configuration, if you already hold the Kimi K3
+shards (they are byte-identical to `moonshotai/Kimi-K3`):
+
+```shell
+hf download Maincode/Matilda-K3 --local-dir ./Matilda-K3 --exclude "model-0*"
+```
+
+Verify after downloading:
+
+```shell
+cd Matilda-K3 && sha256sum -c SHA256SUMS
+```
+
+Plan for about 1.6 TB of disk for the weights and about 30 GB for the runtime image.
+Setting `HF_XET_HIGH_PERFORMANCE=1` speeds up the transfer on fast links.
+
+This is an inference release for the matching runtime. Standalone
+`AutoModel.from_pretrained` loading is not supported.
+
+## Usage
+
+Matilda-K3 is served by the Matilda runtime, a vLLM build with Matilda's
+components compiled in. It exposes an OpenAI-compatible API.
+
+Requirements: one node with 8 × AMD Instinct MI355X (ROCm 7.2 host driver), about
+1.5 TB of fast storage for the weights, and 512 GB or more of host RAM.
+
+The repository includes [`serve.sh`](serve.sh), which checks the model directory and
+GPU devices, pulls the runtime image if needed and starts the server:
+
+```shell
+cd Matilda-K3
+bash serve.sh --wait     # start and block until the API is ready
+bash serve.sh --stop     # stop and remove the container
+```
+
+`MODEL_DIR`, `PORT`, `TP`, `IMAGE`, the cache directories and engine settings such as
+`MAX_MODEL_LEN` can be overridden through environment variables; see the header of
+the script. The equivalent manual command:
+
+```shell
+podman run -d --name matilda-k3 \
+  --device=/dev/kfd --device=/dev/dri --group-add keep-groups --log-driver k8s-file \
+  --network=host --ipc=host --security-opt seccomp=unconfined --ulimit memlock=-1 \
+  -v /path/to/Matilda-K3:/models/Matilda-V3:ro \
+  -v $HOME/matilda-cache:/root/.cache \
+  -v $HOME/matilda-kernel-cfg:/tmp/aiter_configs \
+  docker.io/maincodehq/matilda-vllm:kimi-k3
+```
+
+The first start compiles GPU kernels and can take 20 to 40 minutes; keep the two
+cache directories and later starts take about 10. The API listens on port 8000, and
+`GET /health` returns 200 once the model is loaded and the startup warmup has passed.
+The served model id is `matilda-v3`.
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="unused")
+
+r = client.chat.completions.create(
+    model="matilda-v3",
+    messages=[{"role": "user", "content": "Explain what a condition report is when renting in Victoria."}],
+    max_tokens=400,
+)
+print(r.choices[0].message.content)
+```
+
+Streaming, tool calling (`tools` / `tool_choice`) and the standard sampling
+parameters work as in the OpenAI API.
+
+## Controlling reasoning
+
+Thinking is off by default and is switched on per request through the chat template:
+
+```python
+extra_body={"chat_template_kwargs": {"thinking": True}}
+```
+
+Reasoning text is returned in `message.reasoning` and the answer in
+`message.content`. Give reasoning requests a larger `max_tokens` (1,000 or more).
+
+## Limitations
+
+- **Changed behaviour, not erased knowledge.** Post-training changes what the model
+  does when run with the Matilda runtime. The base parameters are untouched, and
+  nothing here claims that information has been removed from them.
+- **Results are for the tested distributions.** Each bound holds for the stated test
+  set at 95% confidence. It is not a guarantee about arbitrary prompts.
+- **Hardware.** The released runtime targets AMD MI355X on ROCm. Other accelerators
+  need a different runtime build.
+
+## License
+
+The base model weights are licensed under the [Kimi K3 License](LICENSE)
+(Copyright © 2026 Moonshot AI). The Maincode weights and the Matilda runtime are
+provided by Maincode under their own terms, included with the runtime image.
+
+## Intended and Responsible Use
+
+Matilda-K3 is a general-purpose assistant model for chat, writing, analysis,
+coding and agentic work. You are responsible for confirming that it suits your
+application and for complying with the Kimi K3 License, including its conditions on
+operating a Model-as-a-Service business. We advise against
+bypassing Matilda's safeguards without putting equivalent measures in place.
+
+Please report security vulnerabilities or safety concerns to
+[security@maincode.com](mailto:security@maincode.com).

SHA256SUMS

@@ -0,0 +1,110 @@
+20c797ce19af0c17de52c6afb144644768a591c521655f5ebf5712c9850f2887  LICENSE
+ca1156a9b36665d7e6b2f6e4e945995c1cd17a59270e95c60c5d6941ae105186  config.json
+e4bfdfe1fa5171c31db709730d6199c7a518da59cefc6bb095a6c3fea6ee6fdb  configuration_matilda_v3.py
+23fdb17a91ddeb60389aedda384ad45a286db1425722e2115817449e52a47fcf  generation_config.json
+a30a55626a7a755c2b57d1e4c5208da69c94ba5e50a7b416df4a2e8f7edcc3a2  matilda-release.json
+9a3d0249a89a93fdd23d8d249f176d3974d4216cbcbd32e4311732928a7ba6a3  matilda_v3_processor.py
+e13edb6655717547bcd599d64c96a5c6f04c7ab13dc0630e599c05453bb36ba2  matilda_v3_vision_processing.py
+975584c00f85a95fce8ae0f840af8cef69c2ef4db00d34cab3e2cbdfc60f6e51  model-00001-of-000096.safetensors
+26a3284e1d2cb567934ebef002e6a1813551d646739e8bcb1e9e3fe7f878e0f5  model-00002-of-000096.safetensors
+e54af9de4c554956082364010f732443bcd5097390f0121a33fb35e37280b5a9  model-00003-of-000096.safetensors
+5955fd8feda89b1af8400c25e885e7177d47edff155f54b318beb8dd1cec5c05  model-00004-of-000096.safetensors
+d60d68ad0381ffd2d8716d5991a65993cc81837455bf05d1c76ea3a75662e268  model-00005-of-000096.safetensors
+b1d4805767471a9721cd087d2047843ab9262d4f9bbe0d4a306e72c07179f939  model-00006-of-000096.safetensors
+fb1120fef34c0416e73a3259ae6114b9a82b6081871b368a199e0b265cac7df7  model-00007-of-000096.safetensors
+2318dda54fc1985b63d6068de54fbe312ac87317c902666c9075aa5e10e8a1c9  model-00008-of-000096.safetensors
+8b66cdde34f5130cf4f99ec35b16f1f6d33bf0ec946cf2a5612004f5d399f998  model-00009-of-000096.safetensors
+d34f55f7b734a1eaecc986fc7f92bcaa1b7d18fad90a33befd3fae4f1b2771a9  model-00010-of-000096.safetensors
+1738856a4cca2e356510892de4accf3c3f94b9f598b0394a87e7951740ba4a21  model-00011-of-000096.safetensors
+c6b9bef38415f509898fa7b5c04d20c6fee84b0e02c05d74259d201fe6f3868b  model-00012-of-000096.safetensors
+3cbf43d56d9c80be0f848a4866e290741c697e09d885dc2351b0a11de514d9c8  model-00013-of-000096.safetensors
+ce5f343f07d408c64fb247bbe8691edb84d54e3976d3ff586ebcf5929fd143ad  model-00014-of-000096.safetensors
+b55caa8013348498525eef2b1416a657f0c28264ada9b245df19d2eea168b4c1  model-00015-of-000096.safetensors
+5a63e63ced659c1996b02ccabdea977546a39ecce025af1e54552de3bfc0489e  model-00016-of-000096.safetensors
+622bfa605205f4ef65e44dac07246bea79e18123ae8b84ab33eec89b6364c3a9  model-00017-of-000096.safetensors
+838b265ebb86a1320e589685779125d224663160823873b9e5930cf63fafe796  model-00018-of-000096.safetensors
+599a8ecf88f21d4c91295b4160e7564e501807535e522195ee45050a04f17ded  model-00019-of-000096.safetensors
+8e01b61ab76655ca0c5bd6645303a00c05fb58da94e00f978a9ef1e8114a6f0f  model-00020-of-000096.safetensors
+1944265bd024ea6caa23796326e420260a801e5c52e6253155f22ce97e9578d0  model-00021-of-000096.safetensors
+2d32d3e3c8da0764f73830289c6a22224f755c0cf058df0262fb0f83b3777029  model-00022-of-000096.safetensors
+c291f2ec15788cb24cdf791c6d68dbf8803b26d01415cff3fab367cba581a169  model-00023-of-000096.safetensors
+278855ab81d42337e2a1857f136d740911fe3f5b1813dc21ce2cb03dc5c3cde3  model-00024-of-000096.safetensors
+6e3ae6ad868f5b38fa7ddface520796ea251568b07447deee3d164a0a32d862b  model-00025-of-000096.safetensors
+cdd79fb52c7a3350926c4b947ae82cccd0af17fa3fb537c5694a4cedf2b59811  model-00026-of-000096.safetensors
+1d974b40c4aeb5cc0adeba6f9fbad25fc99f8cd39f9dd3513aeb2fb30a9c4188  model-00027-of-000096.safetensors
+1bec58e89ab7835d3ca40e581cc6f047cb93de47fda804eaea4e2407e01c3ed3  model-00028-of-000096.safetensors
+c3bf0e738aa5fbd6ca3ecad982aba8d09efffd58b40cd8fb62d02fe0492f5ceb  model-00029-of-000096.safetensors
+7b996410482ad3c21700ed35d3f2b36282540db92b5631a31aeda1c5e90d6343  model-00030-of-000096.safetensors
+c26689540a2471fe690c441a6cf9bec8f00471930e3131962206fd992e0d377c  model-00031-of-000096.safetensors
+f7dc9e726d46d5c7c2c35af2eea4860cc89dd38a52b60591358a5ca7899c5159  model-00032-of-000096.safetensors
+615afa33b69cbaa42122bb3bcce92e40d6de86713a301c43c5d1bc2ac4342c1b  model-00033-of-000096.safetensors
+a53b27fe92df11e77aec7c5de93ac148b9e2a7bac95020535f68854a7977bde7  model-00034-of-000096.safetensors
+9f4b44c89e4965a973f4fa71eaa0f8ada110f588065541e83bf52692feaa886d  model-00035-of-000096.safetensors
+55aef33fab36df93731289ba38d0ce516d9880c100be5f69f933d0af80bf3c6e  model-00036-of-000096.safetensors
+e95dd3599d6918f5a22bc7b1256aaee9147f40aa05f43135d083d511eb5cbd80  model-00037-of-000096.safetensors
+1ce472771309248fd1155313dc3f72daa6fcc4793fba86d6c5d6a758ff6254ae  model-00038-of-000096.safetensors
+9c75b18c0d3a5088e13973dde519e74ead5c7b1df216dcd623b7ee561f378057  model-00039-of-000096.safetensors
+6f664598c00aee095174db1f860182652ff9b808f53c7764f70e071c6f8a4893  model-00040-of-000096.safetensors
+375f05f94a59d1509bef0976269fceb8f28d40e161d4903e64f735b1ede405c2  model-00041-of-000096.safetensors
+b65947611d6c150394955f4637d4b05007f20a9b1c0f0f02bcf45d0ae2a428ba  model-00042-of-000096.safetensors
+b5a425f100bbfaf804ac2dcca197ccf8fb3a910b6aa79d93e3a103b0146a8309  model-00043-of-000096.safetensors
+113ee012044206e9156dd683cb97ee5f27b07d0a4f936cbda457cd0bcf8ca336  model-00044-of-000096.safetensors
+eb0698659da59c469020a03b3aa8d9ef847fc6359b2513b6720746a44da6f4de  model-00045-of-000096.safetensors
+0270727a399c553a602360b04bc1b5feaf09b22e12e3bb7eea5261801d4a1024  model-00046-of-000096.safetensors
+b38f63eb08036cdf766a078c93ee037630d6481ded26065150915b8deaf03bb8  model-00047-of-000096.safetensors
+131e243c02cf2dc713de108edb8bfdb01c7ee28ce59d0a6615a630fb7cf0e4ae  model-00048-of-000096.safetensors
+72c91dcf2909ead55b6b5234e725227effbcd59fa5ce9f552e91c48d423cef0f  model-00049-of-000096.safetensors
+0a627a082cd39ee7d55f7440a5012c1fe084313f970e7d4351bb08d8ac7f5f2a  model-00050-of-000096.safetensors
+38a37bcec20abe1ddfaf68a636cd61cd291b71d554419a57736fd97d08a8cbff  model-00051-of-000096.safetensors
+9703b632174112ea051aaa2ca8b67558ffbf41a4699d042580ff11f26ec28e0a  model-00052-of-000096.safetensors
+413ec9ea0b693161c5e8a393a7a6be40a9f3c27114a919e1302fe94daeeee621  model-00053-of-000096.safetensors
+0e3da201b765929787e40c2fb8cd0cfb3476bfb9b95d7eb59b7d1066960606a2  model-00054-of-000096.safetensors
+e7c9f4e44f8ac95f73048078c406781fb0418831089fd2f7c55459887606204b  model-00055-of-000096.safetensors
+efd6176016b9fab27cca7710dce7ed599f06bbba1a8b126cfc76781b42c0e880  model-00056-of-000096.safetensors
+e6982c96ac9101b75ab32c56568f5740ddae771acad29d92750b95aeeb3a7a30  model-00057-of-000096.safetensors
+c93a23cbd6530391dcd9ce5617d24fb759e380f5ca676f83d00c8d6a9cda896f  model-00058-of-000096.safetensors
+a62eb822071036421fa4aab662dafe3a3873b1b926378ebf489cddfd48a4d5de  model-00059-of-000096.safetensors
+9bccbaa71b98f8526ca4c6cb091a489063ec4734c84bb5f6d11eeb0512360b5f  model-00060-of-000096.safetensors
+1ae3969540fc676480804c37adc54df77e5ebb923952abb46d398b3a2d612e9d  model-00061-of-000096.safetensors
+96babdc24f2203eed68bd88f8534546696ab35bb1d0db7a5f15aaee295deee68  model-00062-of-000096.safetensors
+8a81caa697a7baf491393d83e3b85e14a0d025f5ee2ca91561528e8aec5c63ea  model-00063-of-000096.safetensors
+325c72d6ca5aaefd020da647ac317621903c8576a97d1de664b93638b7172f39  model-00064-of-000096.safetensors
+276d1cce1d8d494526938d878d4afb713ca379f98064dcd3c505325c954639db  model-00065-of-000096.safetensors
+2ebd83fea628d8cf7496a936f66a8a7f1b430bc8438644ae6ac9761ac056194e  model-00066-of-000096.safetensors
+f0228892f8199c29c5053e7e5388a60dacf1458b53eb6f471e1f548f02478dd1  model-00067-of-000096.safetensors
+fa75764056d16855c42baffd474bcc01045deda7ed5f773d88ff8887ea8458b6  model-00068-of-000096.safetensors
+9375584663bd3073cd95df18c3dc99fd4346c0c71dfdeec686a4891b7768a738  model-00069-of-000096.safetensors
+ab53464148721a209d4941dc3ab6f698574f913179e729726d00ed6232144893  model-00070-of-000096.safetensors
+28ac0d3286ffc5c8567cc3b265500777ba2b75a0a5c6a273c87a5c9cfd8a8a5b  model-00071-of-000096.safetensors
+0a269faaf8ea2daccef499e7c1501089ea05386ca7c6a5a9d4150fd38e37673b  model-00072-of-000096.safetensors
+a1b2e79e1bb7c9e0ade3f0825b748024a5207317589fc57f91dc2540443d716a  model-00073-of-000096.safetensors
+df945022b493373bdcacc3903cc406978342dff2c1b3ace5278b1909fb1d2479  model-00074-of-000096.safetensors
+8c6d7cb12f7c51aa88207c5b9410fccfa44e4a9022efc75d73c06054c1296c05  model-00075-of-000096.safetensors
+d5174eb5de19274b0fe62d466bfb21bac3b03d6d9676b801c6fea1ed57657998  model-00076-of-000096.safetensors
+8707eacfd69e8be65c7052551834e7ac26945b9ddf915939e08f5eb813c6a262  model-00077-of-000096.safetensors
+2773d41de168c7373bf2f7f9994cbbb2712c379503578d8462aa783db7cba128  model-00078-of-000096.safetensors
+da02c8a46b81f42a64330e0e31478dcd7b020633a65251b535817431bba1d96b  model-00079-of-000096.safetensors
+96b5accdf3bc2b4651979361fa7f6191197b8573c36ab6a58effce487402b177  model-00080-of-000096.safetensors
+01562aa616ea3dc398a7c40b4d9c3c4700885541efeaed6dbd1ba8076cae9c4b  model-00081-of-000096.safetensors
+8cba090734d9a3900276cca442bd6fa60f5206ce0c70884f7b2df3df877485bd  model-00082-of-000096.safetensors
+6ceebf8ce621712dd3185943224ca83a45f5bc310c272df7dee4b69e3dfc87fe  model-00083-of-000096.safetensors
+c3f1318e7e1cc6893230a14c229a0c9ec0037cb1d0912a395f9222a3e8a8bc2d  model-00084-of-000096.safetensors
+633b2e3b86ec35f87fa4216b14bba49fc4058a1296433bc22b0576925118b6ad  model-00085-of-000096.safetensors
+add4056ab3ecaa7befdac2e00280d294ce470d541917ac90df8fc50497df7fb0  model-00086-of-000096.safetensors
+f6d608f2c40b584b775db184013e37740d4710abad414c584408e0ad09fb486b  model-00087-of-000096.safetensors
+87afe43b8a71d2cc56787a976f52f8c35bcfbe85df7d0c445194bc1f4d7e0c4a  model-00088-of-000096.safetensors
+24016b28cfdf9420ae2f411145ef919cf2e1ec667830aded439bfb761c61755f  model-00089-of-000096.safetensors
+1ecd85dbd77ce081f6238b894f8a7da2ff40346da7042c427a52d83562dbb5ea  model-00090-of-000096.safetensors
+a4e666132aed052b4bf174f56853b70cbb2ada898fe568f60e0cdf3ad46a0a4a  model-00091-of-000096.safetensors
+359848294be55e1c8949f0a4c92098bc73276895289fd1123f10769ba685e248  model-00092-of-000096.safetensors
+d31d58d1bd3fcb8c350ef497d2acd23e0fe768ab5c0621e60f20b03d611f64e6  model-00093-of-000096.safetensors
+ad66e1cb96b86963e63d6a0a466b6a407b13c9815cb480fe612480cc6bb3b6e1  model-00094-of-000096.safetensors
+01d41139abb8cf3b5288a97318cc4ab92676671b4eb141031cd80d7c3ced6122  model-00095-of-000096.safetensors
+9d10c74fc10161bef9463a8541a634a97f521f43c99368ea7243ce0c79cdbf7c  model-00096-of-000096.safetensors
+f33675c95c69fbd79f42d83e7783677e430d235419914fa7ca717ace153da835  model.safetensors.index.json
+7c485bb6cadd5c1775c07374d1c0002f10574b1ff2ae7d4074cfe0996771d8f6  preprocessor_config.json
+af2da849c1a68b44b858347058da82d0be3324ac249e87eb5cbbf0a27d9469c2  runtime/adapters.safetensors
+bcb65ce4b1cb48f17ad9861d3a496efe43aef78c76b04f1ddabaa93b919cf9d9  serve.sh
+b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103  tiktoken.model
+38df0f503eae602715e9706c06eb097f8a2dabc4c4150f17582dd5f30303e872  tokenization_matilda.py
+402b23e8ec08f684cecf37233cd6b693caf5a286681d786b15b892ab6afeda6f  tokenizer_config.json

config.json

@@ -0,0 +1,305 @@
+{
+  "architectures": [
+    "MatildaV3ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_matilda_v3.MatildaV3Config"
+  },
+  "bos_token_id": 163584,
+  "dtype": "bfloat16",
+  "eos_token_id": 163586,
+  "ignore_index": -100,
+  "image_placeholder": "<|kimi_image_placeholder|>",
+  "media_placeholder_token_id": 163605,
+  "model_type": "matilda_v3",
+  "pad_token_id": 163839,
+  "text_config": {
+    "_name_or_path": "",
+    "activation_situ_beta": 4.0,
+    "activation_situ_linear_beta": 25.0,
+    "add_cross_attention": false,
+    "architectures": [
+      "MatildaLinearForCausalLM"
+    ],
+    "attn_res_block_size": 12,
+    "auto_map": {
+      "AutoConfig": "configuration_matilda_v3.MatildaLinearConfig"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 163584,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": "bfloat16",
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 163586,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "first_k_dense_replace": 1,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "situ",
+    "hidden_size": 7168,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 33792,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kv_lora_rank": 512,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_moe_use_norm": true,
+    "length_penalty": 1.0,
+    "linear_attn_config": {
+      "full_attn_layers": [
+        4,
+        8,
+        12,
+        16,
+        20,
+        24,
+        28,
+        32,
+        36,
+        40,
+        44,
+        48,
+        52,
+        56,
+        60,
+        64,
+        68,
+        72,
+        76,
+        80,
+        84,
+        88,
+        92,
+        93
+      ],
+      "gate_lower_bound": -5.0,
+      "head_dim": 128,
+      "kda_layers": [
+        1,
+        2,
+        3,
+        5,
+        6,
+        7,
+        9,
+        10,
+        11,
+        13,
+        14,
+        15,
+        17,
+        18,
+        19,
+        21,
+        22,
+        23,
+        25,
+        26,
+        27,
+        29,
+        30,
+        31,
+        33,
+        34,
+        35,
+        37,
+        38,
+        39,
+        41,
+        42,
+        43,
+        45,
+        46,
+        47,
+        49,
+        50,
+        51,
+        53,
+        54,
+        55,
+        57,
+        58,
+        59,
+        61,
+        62,
+        63,
+        65,
+        66,
+        67,
+        69,
+        70,
+        71,
+        73,
+        74,
+        75,
+        77,
+        78,
+        79,
+        81,
+        82,
+        83,
+        85,
+        86,
+        87,
+        89,
+        90,
+        91
+      ],
+      "num_heads": 96,
+      "short_conv_kernel_size": 4,
+      "use_full_rank_gate": true
+    },
+    "max_length": 20,
+    "max_position_embeddings": 1048576,
+    "min_length": 0,
+    "mla_use_nope": true,
+    "mla_use_output_gate": true,
+    "model_type": "matilda_linear",
+    "moe_intermediate_size": 3072,
+    "moe_layer_freq": 1,
+    "moe_renormalize": true,
+    "moe_router_activation_func": "sigmoid",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 96,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_expert_group": 1,
+    "num_experts": 896,
+    "num_experts_per_token": 16,
+    "num_hidden_layers": 93,
+    "num_key_value_heads": 96,
+    "num_nextn_predict_layers": 0,
+    "num_return_sequences": 1,
+    "num_shared_experts": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 163839,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization_config": {
+      "config_groups": {
+        "group_0": {
+          "format": "mxfp4-pack-quantized",
+          "input_activations": null,
+          "output_activations": null,
+          "targets": [
+            "Linear"
+          ],
+          "weights": {
+            "actorder": null,
+            "block_structure": null,
+            "dynamic": false,
+            "group_size": 32,
+            "num_bits": 4,
+            "observer": "minmax",
+            "observer_kwargs": {},
+            "scale_dtype": "torch.uint8",
+            "strategy": "group",
+            "symmetric": true,
+            "type": "float",
+            "zp_dtype": null
+          }
+        }
+      },
+      "format": "mxfp4-pack-quantized",
+      "global_compression_ratio": null,
+      "ignore": [
+        "re:.*self_attn.*",
+        "re:.*shared_experts.*",
+        "re:.*mlp\\.(gate|up|gate_up|down)_proj.*",
+        "re:.*lm_head.*",
+        "re:.*vision_tower.*",
+        "re:.*mm_projector.*",
+        "re:.*routed_expert_(up|down)_proj.*",
+        "re:.*(self_attention_res_proj|mlp_res_proj|output_attn_res_proj).*",
+        "re:.*matilda_pol_A$",
+        "re:.*matilda_pol_B$",
+        "re:.*matilda_id_A$",
+        "re:.*matilda_id_B$",
+        "re:.*matilda_probes.*",
+        "re:.*_trigger_probe.*",
+        "re:.*_extra_probes.*"
+      ],
+      "kv_cache_scheme": null,
+      "quant_method": "compressed-tensors",
+      "quantization_status": "compressed"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "routed_expert_hidden_size": 3584,
+    "routed_scaling_factor": 1.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "torchscript": false,
+    "transformers_version": "4.56.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_grouped_topk": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840
+  },
+  "tie_word_embeddings": false,
+  "vision_config": {
+    "_attn_implementation": "flash_attention_2",
+    "activation_func": "gelu_pytorch_tanh",
+    "attn_bias": false,
+    "init_pos_emb_height": 64,
+    "init_pos_emb_time": 4,
+    "init_pos_emb_width": 64,
+    "linear_bias": false,
+    "merge_kernel_size": [
+      2,
+      2
+    ],
+    "merge_type": "sd2_tpool",
+    "mlp_type": "mlp2",
+    "mm_hidden_size": 1024,
+    "mm_projector_type": "patchmergerv2",
+    "norm_type": "rmsnorm",
+    "patch_embed_proj_bias": false,
+    "patch_size": 14,
+    "pos_emb_interpolation_mode": "bilinear",
+    "pos_emb_type": "divided_fixed",
+    "projector_hidden_act": "gelu",
+    "projector_ln_eps": 1e-05,
+    "qkv_hidden_size": 1536,
+    "text_hidden_size": 7168,
+    "vt_hidden_size": 1024,
+    "vt_intermediate_size": 4096,
+    "vt_num_attention_heads": 12,
+    "vt_num_hidden_layers": 27
+  }
+}

configuration_matilda_v3.py

@@ -0,0 +1 @@
+from matilda_components.configuration_matilda_v3 import MatildaV3Config, MatildaLinearConfig, MatildaV3VisionConfig

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_length": 1048576,
+  "eos_token_id": 163586
+}

matilda-release.json

@@ -0,0 +1,159 @@
+{
+  "version": 1,
+  "dense_shards": 96,
+  "dense_tensor_keys": 497220,
+  "inactive_integrated_gate_keys_omitted": 1612,
+  "dense_weights_hardlinked_to_original": true,
+  "adapter_payload_sha256": "af2da849c1a68b44b858347058da82d0be3324ac249e87eb5cbbf0a27d9469c2",
+  "metadata": {
+    "LICENSE": {
+      "size": 3065,
+      "sha256": "20c797ce19af0c17de52c6afb144644768a591c521655f5ebf5712c9850f2887"
+    },
+    "config.json": {
+      "size": 7094,
+      "sha256": "ca1156a9b36665d7e6b2f6e4e945995c1cd17a59270e95c60c5d6941ae105186"
+    },
+    "configuration_matilda_v3.py": {
+      "size": 116,
+      "sha256": "e4bfdfe1fa5171c31db709730d6199c7a518da59cefc6bb095a6c3fea6ee6fdb"
+    },
+    "generation_config.json": {
+      "size": 54,
+      "sha256": "23fdb17a91ddeb60389aedda384ad45a286db1425722e2115817449e52a47fcf"
+    },
+    "matilda_v3_processor.py": {
+      "size": 71,
+      "sha256": "9a3d0249a89a93fdd23d8d249f176d3974d4216cbcbd32e4311732928a7ba6a3"
+    },
+    "matilda_v3_vision_processing.py": {
+      "size": 85,
+      "sha256": "e13edb6655717547bcd599d64c96a5c6f04c7ab13dc0630e599c05453bb36ba2"
+    },
+    "model.safetensors.index.json": {
+      "size": 59764097,
+      "sha256": "f33675c95c69fbd79f42d83e7783677e430d235419914fa7ca717ace153da835"
+    },
+    "preprocessor_config.json": {
+      "size": 1024,
+      "sha256": "7c485bb6cadd5c1775c07374d1c0002f10574b1ff2ae7d4074cfe0996771d8f6"
+    },
+    "tiktoken.model": {
+      "size": 2795286,
+      "sha256": "b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103"
+    },
+    "tokenization_matilda.py": {
+      "size": 70,
+      "sha256": "38df0f503eae602715e9706c06eb097f8a2dabc4c4150f17582dd5f30303e872"
+    },
+    "tokenizer_config.json": {
+      "size": 3482,
+      "sha256": "402b23e8ec08f684cecf37233cd6b693caf5a286681d786b15b892ab6afeda6f"
+    }
+  },
+  "python_files": [
+    "configuration_matilda_v3.py",
+    "matilda_v3_processor.py",
+    "matilda_v3_vision_processing.py",
+    "tokenization_matilda.py"
+  ],
+  "python_scope": "Import-only bridges to compiled container modules; no model implementation",
+  "dense_source_sizes": {
+    "model-00001-of-000096.safetensors": 2341216112,
+    "model-00002-of-000096.safetensors": 16990911504,
+    "model-00003-of-000096.safetensors": 16990911504,
+    "model-00004-of-000096.safetensors": 16567501776,
+    "model-00005-of-000096.safetensors": 16990911504,
+    "model-00006-of-000096.safetensors": 16990911504,
+    "model-00007-of-000096.safetensors": 16990911504,
+    "model-00008-of-000096.safetensors": 16567501776,
+    "model-00009-of-000096.safetensors": 16990911504,
+    "model-00010-of-000096.safetensors": 16990911504,
+    "model-00011-of-000096.safetensors": 16990916912,
+    "model-00012-of-000096.safetensors": 16567507176,
+    "model-00013-of-000096.safetensors": 16990916912,
+    "model-00014-of-000096.safetensors": 16990916912,
+    "model-00015-of-000096.safetensors": 16990916912,
+    "model-00016-of-000096.safetensors": 16567507176,
+    "model-00017-of-000096.safetensors": 16990916912,
+    "model-00018-of-000096.safetensors": 16990916912,
+    "model-00019-of-000096.safetensors": 16990916912,
+    "model-00020-of-000096.safetensors": 16567507176,
+    "model-00021-of-000096.safetensors": 16990916912,
+    "model-00022-of-000096.safetensors": 16990916912,
+    "model-00023-of-000096.safetensors": 16990916912,
+    "model-00024-of-000096.safetensors": 16567507176,
+    "model-00025-of-000096.safetensors": 16990916912,
+    "model-00026-of-000096.safetensors": 16990916912,
+    "model-00027-of-000096.safetensors": 16990916912,
+    "model-00028-of-000096.safetensors": 16567507176,
+    "model-00029-of-000096.safetensors": 16990916912,
+    "model-00030-of-000096.safetensors": 16990916912,
+    "model-00031-of-000096.safetensors": 16990916912,
+    "model-00032-of-000096.safetensors": 16567507176,
+    "model-00033-of-000096.safetensors": 16990916912,
+    "model-00034-of-000096.safetensors": 16990916912,
+    "model-00035-of-000096.safetensors": 16990916912,
+    "model-00036-of-000096.safetensors": 16567507176,
+    "model-00037-of-000096.safetensors": 16990916912,
+    "model-00038-of-000096.safetensors": 16990916912,
+    "model-00039-of-000096.safetensors": 16990916912,
+    "model-00040-of-000096.safetensors": 16567507176,
+    "model-00041-of-000096.safetensors": 16990916912,
+    "model-00042-of-000096.safetensors": 16990916912,
+    "model-00043-of-000096.safetensors": 16990916912,
+    "model-00044-of-000096.safetensors": 16567507176,
+    "model-00045-of-000096.safetensors": 16990916912,
+    "model-00046-of-000096.safetensors": 16990916912,
+    "model-00047-of-000096.safetensors": 16990916912,
+    "model-00048-of-000096.safetensors": 16567507176,
+    "model-00049-of-000096.safetensors": 16990916912,
+    "model-00050-of-000096.safetensors": 16990916912,
+    "model-00051-of-000096.safetensors": 16990916912,
+    "model-00052-of-000096.safetensors": 16567507176,
+    "model-00053-of-000096.safetensors": 16990916912,
+    "model-00054-of-000096.safetensors": 16990916912,
+    "model-00055-of-000096.safetensors": 16990916912,
+    "model-00056-of-000096.safetensors": 16567507176,
+    "model-00057-of-000096.safetensors": 16990916912,
+    "model-00058-of-000096.safetensors": 16990916912,
+    "model-00059-of-000096.safetensors": 16990916912,
+    "model-00060-of-000096.safetensors": 16567507176,
+    "model-00061-of-000096.safetensors": 16990916912,
+    "model-00062-of-000096.safetensors": 16990916912,
+    "model-00063-of-000096.safetensors": 16990916912,
+    "model-00064-of-000096.safetensors": 16567507176,
+    "model-00065-of-000096.safetensors": 16990916912,
+    "model-00066-of-000096.safetensors": 16990916912,
+    "model-00067-of-000096.safetensors": 16990916912,
+    "model-00068-of-000096.safetensors": 16567507176,
+    "model-00069-of-000096.safetensors": 16990916912,
+    "model-00070-of-000096.safetensors": 16990916912,
+    "model-00071-of-000096.safetensors": 16990916912,
+    "model-00072-of-000096.safetensors": 16567507176,
+    "model-00073-of-000096.safetensors": 16990916912,
+    "model-00074-of-000096.safetensors": 16990916912,
+    "model-00075-of-000096.safetensors": 16990916912,
+    "model-00076-of-000096.safetensors": 16567507176,
+    "model-00077-of-000096.safetensors": 16990916912,
+    "model-00078-of-000096.safetensors": 16990916912,
+    "model-00079-of-000096.safetensors": 16990916912,
+    "model-00080-of-000096.safetensors": 16567507176,
+    "model-00081-of-000096.safetensors": 16990916912,
+    "model-00082-of-000096.safetensors": 16990916912,
+    "model-00083-of-000096.safetensors": 16990916912,
+    "model-00084-of-000096.safetensors": 16567507176,
+    "model-00085-of-000096.safetensors": 16990916912,
+    "model-00086-of-000096.safetensors": 16990916912,
+    "model-00087-of-000096.safetensors": 16990916912,
+    "model-00088-of-000096.safetensors": 16567507176,
+    "model-00089-of-000096.safetensors": 16990916912,
+    "model-00090-of-000096.safetensors": 16990916912,
+    "model-00091-of-000096.safetensors": 16990916912,
+    "model-00092-of-000096.safetensors": 16567507176,
+    "model-00093-of-000096.safetensors": 16567507176,
+    "model-00094-of-000096.safetensors": 4697664072,
+    "model-00095-of-000096.safetensors": 92289328,
+    "model-00096-of-000096.safetensors": 802448352
+  }
+}

matilda_v3_processor.py

@@ -0,0 +1 @@
+from matilda_components.matilda_v3_processor import MatildaV3Processor

matilda_v3_vision_processing.py

@@ -0,0 +1 @@
+from matilda_components.matilda_v3_vision_processing import MatildaV3VisionProcessor

model-00001-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975584c00f85a95fce8ae0f840af8cef69c2ef4db00d34cab3e2cbdfc60f6e51
+size 2341216112

model-00002-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a3284e1d2cb567934ebef002e6a1813551d646739e8bcb1e9e3fe7f878e0f5
+size 16990911504

model-00003-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54af9de4c554956082364010f732443bcd5097390f0121a33fb35e37280b5a9
+size 16990911504

model-00004-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5955fd8feda89b1af8400c25e885e7177d47edff155f54b318beb8dd1cec5c05
+size 16567501776

model-00005-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60d68ad0381ffd2d8716d5991a65993cc81837455bf05d1c76ea3a75662e268
+size 16990911504

model-00006-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d4805767471a9721cd087d2047843ab9262d4f9bbe0d4a306e72c07179f939
+size 16990911504

model-00007-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1120fef34c0416e73a3259ae6114b9a82b6081871b368a199e0b265cac7df7
+size 16990911504

model-00008-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2318dda54fc1985b63d6068de54fbe312ac87317c902666c9075aa5e10e8a1c9
+size 16567501776

model-00009-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b66cdde34f5130cf4f99ec35b16f1f6d33bf0ec946cf2a5612004f5d399f998
+size 16990911504

model-00010-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34f55f7b734a1eaecc986fc7f92bcaa1b7d18fad90a33befd3fae4f1b2771a9
+size 16990911504

model-00011-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1738856a4cca2e356510892de4accf3c3f94b9f598b0394a87e7951740ba4a21
+size 16990916912

model-00012-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b9bef38415f509898fa7b5c04d20c6fee84b0e02c05d74259d201fe6f3868b
+size 16567507176

model-00013-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbf43d56d9c80be0f848a4866e290741c697e09d885dc2351b0a11de514d9c8
+size 16990916912

model-00014-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5f343f07d408c64fb247bbe8691edb84d54e3976d3ff586ebcf5929fd143ad
+size 16990916912

model-00015-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55caa8013348498525eef2b1416a657f0c28264ada9b245df19d2eea168b4c1
+size 16990916912

model-00016-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a63e63ced659c1996b02ccabdea977546a39ecce025af1e54552de3bfc0489e
+size 16567507176

model-00017-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622bfa605205f4ef65e44dac07246bea79e18123ae8b84ab33eec89b6364c3a9
+size 16990916912

model-00018-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838b265ebb86a1320e589685779125d224663160823873b9e5930cf63fafe796
+size 16990916912

model-00019-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599a8ecf88f21d4c91295b4160e7564e501807535e522195ee45050a04f17ded
+size 16990916912

model-00020-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e01b61ab76655ca0c5bd6645303a00c05fb58da94e00f978a9ef1e8114a6f0f
+size 16567507176

model-00021-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1944265bd024ea6caa23796326e420260a801e5c52e6253155f22ce97e9578d0
+size 16990916912

model-00022-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d32d3e3c8da0764f73830289c6a22224f755c0cf058df0262fb0f83b3777029
+size 16990916912

model-00023-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c291f2ec15788cb24cdf791c6d68dbf8803b26d01415cff3fab367cba581a169
+size 16990916912

model-00024-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278855ab81d42337e2a1857f136d740911fe3f5b1813dc21ce2cb03dc5c3cde3
+size 16567507176

model-00025-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3ae6ad868f5b38fa7ddface520796ea251568b07447deee3d164a0a32d862b
+size 16990916912

model-00026-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd79fb52c7a3350926c4b947ae82cccd0af17fa3fb537c5694a4cedf2b59811
+size 16990916912

model-00027-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d974b40c4aeb5cc0adeba6f9fbad25fc99f8cd39f9dd3513aeb2fb30a9c4188
+size 16990916912

model-00028-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bec58e89ab7835d3ca40e581cc6f047cb93de47fda804eaea4e2407e01c3ed3
+size 16567507176

model-00029-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bf0e738aa5fbd6ca3ecad982aba8d09efffd58b40cd8fb62d02fe0492f5ceb
+size 16990916912

model-00030-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b996410482ad3c21700ed35d3f2b36282540db92b5631a31aeda1c5e90d6343
+size 16990916912

model-00031-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26689540a2471fe690c441a6cf9bec8f00471930e3131962206fd992e0d377c
+size 16990916912

model-00032-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dc9e726d46d5c7c2c35af2eea4860cc89dd38a52b60591358a5ca7899c5159
+size 16567507176

model-00033-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615afa33b69cbaa42122bb3bcce92e40d6de86713a301c43c5d1bc2ac4342c1b
+size 16990916912

model-00034-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53b27fe92df11e77aec7c5de93ac148b9e2a7bac95020535f68854a7977bde7
+size 16990916912

model-00035-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4b44c89e4965a973f4fa71eaa0f8ada110f588065541e83bf52692feaa886d
+size 16990916912

model-00036-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55aef33fab36df93731289ba38d0ce516d9880c100be5f69f933d0af80bf3c6e
+size 16567507176

model-00037-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95dd3599d6918f5a22bc7b1256aaee9147f40aa05f43135d083d511eb5cbd80
+size 16990916912

model-00038-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce472771309248fd1155313dc3f72daa6fcc4793fba86d6c5d6a758ff6254ae
+size 16990916912

model-00039-of-000096.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c75b18c0d3a5088e13973dde519e74ead5c7b1df216dcd623b7ee561f378057
+size 16990916912