Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,8 @@
+. filter=lfs diff=lfs merge=lfs -text
+infinitystar_8b_480p_weights filter=lfs diff=lfs merge=lfs -text
+infinitystar_8b_720p_weights filter=lfs diff=lfs merge=lfs -text
+infinitystar_videovae.pth filter=lfs diff=lfs merge=lfs -text
+text_encoder filter=lfs diff=lfs merge=lfs -text
+.gitattributes filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder/flan-t5-xl-official/spiece.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+license: mit
+language:
+- en
+---
+# Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
+
+<div align="center">
+
+<!-- [![demo platform](https://img.shields.io/badge/Play%20with%20Infinity%21-Infinity%20demo%20platform-lightblue)](https://opensource.bytedance.com/gmpt/t2i/invite)&nbsp;
+[![arXiv](https://img.shields.io/static/v1?label=Project%20Page&message=Github&color=blue&logo=github-pages)](https://foundationvision.github.io/infinity.project/)&nbsp;
+[![arXiv](https://img.shields.io/badge/arXiv%20paper-2412.04431-b31b1b.svg)](https://arxiv.org/abs/2412.04431)&nbsp;
+[![huggingface weights](https://img.shields.io/badge/%F0%9F%A4%97%20Weights-FoundationVision/Infinity-yellow)](https://huggingface.co/FoundationVision/infinity)&nbsp;
+[![code](https://img.shields.io/badge/%F0%9F%A4%96%20Code-FoundationVision/Infinity-green)](https://github.com/FoundationVision/InfinityStar)&nbsp;
+
+</div>
+<p align="center" style="font-size: larger;">
+  <a href="https://arxiv.org/abs/2412.04431">Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation</a>
+</p> -->
+
+
+
+
+## 📖 Introduction
+We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long-duration video synthesis via straightforward temporal autoregression. Through extensive experiments, InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10$\times$ faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial-level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation.
+
+## 📌 Note
+This repo is used for hosting InfinityStar's checkpoints. For more details, please refer to [![code](https://img.shields.io/badge/%F0%9F%A4%96%20Code-FoundationVision/Infinity-green)](https://github.com/FoundationVision/InfinityStar)&nbsp;
+
+## 📖 Citation
+If our work assists your research, feel free to give us a star ⭐ or cite us using:
+
+```
+@misc{han2024infinityscalingbitwiseautoregressive,
+    title={Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis}, 
+    author={Jian Han and Jinlai Liu and Yi Jiang and Bin Yan and Yuqi Zhang and Zehuan Yuan and Bingyue Peng and Xiaobing Liu},
+    year={2024},
+    eprint={2412.04431},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV},
+    url={https://arxiv.org/abs/2412.04431}, 
+}
+```

config.json

@@ -0,0 +1,5 @@
+{
+  "Name": [
+    "InfinityStar"
+  ],
+}

infinitystar_8b_480p_weights/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1023f0b69f1fd41ea71788559d57fd92bf9d530378cd0aa95836bdb83c1abbd
+size 5838681840

infinitystar_8b_480p_weights/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5e53a3fe916222e357b5a51f0150f97e50e5f245b48d324dfbba781865a2b2
+size 5838681840

infinitystar_8b_480p_weights/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069bb0e28dddcb4e51e4bb84fdf5d4dc03d50ac87bcc652a4468dbd8fe67df7c
+size 5838681840

infinitystar_8b_480p_weights/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822c41b75bec76332898efc5eba4af53ba720dd00323996e42ed4696dca84292
+size 5838681840

infinitystar_8b_480p_weights/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d960b70b4e757df48af32587b5547c2dd03a346446bbfdc1d90b64faba0ca42a
+size 5838681840

infinitystar_8b_480p_weights/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15fb291e561f41a260a6f7dd03a56430ef048fab21ac036c6775dd045db8de6a
+size 5880167760

infinitystar_8b_480p_weights/model.safetensors.index.json

@@ -0,0 +1,414 @@
+{
+  "metadata": {
+    "total_size": 35073528832
+  },
+  "weight_map": {
+    "block_chunks.0.module.0.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.0.module.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.1.module.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.0.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.1.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.2.module.5.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.0.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.1.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.2.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.4.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.3.module.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.0.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.1.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.2.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.3.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.4.module.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "text_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.0.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.1.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.2.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.3.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.4.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.5.module.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "text_proj.bias": "model-00006-of-00006.safetensors",
+    "word_embed.weight": "model-00006-of-00006.safetensors",
+    "word_embed.bias": "model-00006-of-00006.safetensors",
+    "norm_hidden_sates.weight": "model-00006-of-00006.safetensors",
+    "head.weight": "model-00006-of-00006.safetensors",
+    "head.bias": "model-00006-of-00006.safetensors",
+    "semantic_head2.weight": "model-00006-of-00006.safetensors",
+    "semantic_head2.bias": "model-00006-of-00006.safetensors",
+    "cfg_uncond": "model-00006-of-00006.safetensors",
+    "sos_token": "model-00006-of-00006.safetensors"
+  }
+}

infinitystar_8b_720p_weights/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acb5a5444101b34ec32066a8b0cccc8d1f76de6c90e262b5bbda518017d0a38
+size 5838681840

infinitystar_8b_720p_weights/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498bb93b0a3f59428217b56fd13b0697255af98fb0ef0325f0bd026cb602d8eb
+size 5838681840

infinitystar_8b_720p_weights/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6d0d8e63a2c69836c1f6434b4726604ba91d857192e5ee0b15a639604b96e4
+size 5838681840

infinitystar_8b_720p_weights/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3451ec0afd2c8df52f6b8d13cc79d245219883e991ce325203b5e50d3100b6d2
+size 5838681840

infinitystar_8b_720p_weights/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533a4dce3a9f8975dddf2ebe24b414e871341bab395b59d37c909c0b8206ab84
+size 5880167760

infinitystar_8b_720p_weights/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5f5cdf26195e1cd3578942543ac14647b12e9a21ddfd8c02a4ec1ec4d184f7
+size 5838681840

infinitystar_8b_720p_weights/model.safetensors.index.json

@@ -0,0 +1,414 @@
+{
+  "metadata": {
+    "total_size": 35073528448
+  },
+  "weight_map": {
+    "block_chunks.2.module.0.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.2.module.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.3.module.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.0.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.1.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.4.module.5.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.0.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.1.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.2.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.4.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.0.module.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "text_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.0.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.1.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.2.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.3.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "block_chunks.5.module.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "text_proj.bias": "model-00005-of-00006.safetensors",
+    "word_embed.weight": "model-00005-of-00006.safetensors",
+    "word_embed.bias": "model-00005-of-00006.safetensors",
+    "norm_hidden_sates.weight": "model-00005-of-00006.safetensors",
+    "head.weight": "model-00005-of-00006.safetensors",
+    "head.bias": "model-00005-of-00006.safetensors",
+    "semantic_head2.weight": "model-00005-of-00006.safetensors",
+    "semantic_head2.bias": "model-00005-of-00006.safetensors",
+    "cfg_uncond": "model-00005-of-00006.safetensors",
+    "sos_token": "model-00005-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.0.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.1.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.2.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.3.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.4.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "block_chunks.1.module.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors"
+  }
+}

infinitystar_videovae.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4d7248f463ed8af63ae41755a036973c1a248b9073bef3689a19b3d38772b2
+size 738766996

text_encoder/flan-t5-xl-official/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder/flan-t5-xl-official/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

text_encoder/flan-t5-xl-official/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99196ddfbe886e8ef860f52de979df64890edfc792c3d94ce0502991f347dd18
+size 9449619912

text_encoder/flan-t5-xl-official/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c677ddeb21009b6efd97146f37fc3a0396707fb5e63ade7aff64884dce9806
+size 1949477672

text_encoder/flan-t5-xl-official/model.safetensors.index.json

@@ -0,0 +1,567 @@
+{
+    "metadata": {
+        "total_size": 11925413888
+    },
+    "weight_map": {
+        "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.0.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.1.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.10.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.11.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.12.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.13.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.14.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.15.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.16.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.2.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.3.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.4.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.5.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.6.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.7.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.8.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "decoder.block.9.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "shared.weight": "model-00001-of-00002.safetensors"
+    }
+}

text_encoder/flan-t5-xl-official/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

text_encoder/flan-t5-xl-official/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

text_encoder/flan-t5-xl-official/tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "google/t5-v1_1-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}