Text-to-Video
Safetensors
MLX
Wan2.2
mlx-gen
mflux
apple-silicon
8-bit precision
mixed-q8-bf16
wan
video-generation
wan-a14b
Instructions to use AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir wan2.2-t2v-a14b-diffusers-8bit AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit
- Wan2.2
How to use AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +93 -0
- model_index.json +29 -0
- scheduler/scheduler_config.json +30 -0
- text_encoder/config.json +34 -0
- text_encoder/model-00001-of-00003.safetensors +3 -0
- text_encoder/model-00002-of-00003.safetensors +3 -0
- text_encoder/model-00003-of-00003.safetensors +3 -0
- text_encoder/model.safetensors.index.json +249 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +317 -0
- transformer/0.safetensors +3 -0
- transformer/1.safetensors +3 -0
- transformer/2.safetensors +3 -0
- transformer/3.safetensors +3 -0
- transformer/4.safetensors +3 -0
- transformer/5.safetensors +3 -0
- transformer/6.safetensors +3 -0
- transformer/7.safetensors +3 -0
- transformer/model.safetensors.index.json +0 -0
- transformer_2/0.safetensors +3 -0
- transformer_2/1.safetensors +3 -0
- transformer_2/2.safetensors +3 -0
- transformer_2/3.safetensors +3 -0
- transformer_2/4.safetensors +3 -0
- transformer_2/5.safetensors +3 -0
- transformer_2/6.safetensors +3 -0
- transformer_2/7.safetensors +3 -0
- transformer_2/model.safetensors.index.json +0 -0
- vae/0.safetensors +3 -0
- vae/model.safetensors.index.json +202 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Wan-AI/Wan2.2-T2V-A14B-Diffusers
|
| 4 |
+
pipeline_tag: text-to-video
|
| 5 |
+
library_name: mlx-gen
|
| 6 |
+
tags:
|
| 7 |
+
- mlx
|
| 8 |
+
- mlx-gen
|
| 9 |
+
- mflux
|
| 10 |
+
- apple-silicon
|
| 11 |
+
- 8-bit
|
| 12 |
+
- wan
|
| 13 |
+
- wan2.2
|
| 14 |
+
- video-generation
|
| 15 |
+
- text-to-video
|
| 16 |
+
- image-to-video
|
| 17 |
+
- wan-a14b
|
| 18 |
+
---
|
| 19 |
+
# wan2.2-t2v-a14b-diffusers-8bit
|
| 20 |
+
|
| 21 |
+
This repository contains MLX-Gen saved weights for `Wan-AI/Wan2.2-T2V-A14B-Diffusers`. The checkpoint is designed for local Apple Silicon inference with [`mlx-gen`](https://github.com/lpalbou/mlx-gen).
|
| 22 |
+
|
| 23 |
+
It uses the mflux/MLX saved-weight layout and MLX quantization tensors. It is not a Diffusers or Transformers `from_pretrained()` checkpoint.
|
| 24 |
+
|
| 25 |
+
## Source Model
|
| 26 |
+
|
| 27 |
+
Original model: [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers).
|
| 28 |
+
|
| 29 |
+
## License and Access
|
| 30 |
+
|
| 31 |
+
This quantized derivative follows the Apache 2.0 license of the source model.
|
| 32 |
+
|
| 33 |
+
## Quantization
|
| 34 |
+
|
| 35 |
+
This is an MLX q8 checkpoint for Wan2.2 A14B. MLX-Gen uses 8-bit quantization for Wan modules where MLX supports quantization:
|
| 36 |
+
|
| 37 |
+
- q8 for quantizable Wan transformer attention and feed-forward modules.
|
| 38 |
+
- BF16 for the Wan VAE.
|
| 39 |
+
- BF16 for Wan transformer conditioning/output projection linears, the UMT5 text encoder, scheduler metadata, tokenizer files, norms, and other non-quantizable parameters.
|
| 40 |
+
|
| 41 |
+
Wan q4 quality and any possible mixed q4/q8 policy are still under validation. Prefer q8 for publishable Wan checkpoints until the q4 policy is documented.
|
| 42 |
+
|
| 43 |
+
See the [MLX-Gen quantization docs](https://github.com/lpalbou/mlx-gen/blob/main/docs/quantization.md) for compatibility notes.
|
| 44 |
+
|
| 45 |
+
## Local Validation
|
| 46 |
+
|
| 47 |
+
Validation used 384x224, 17 frames, 12 denoising steps, guidance 4, guidance-2 3, fps 8, and seed 4242 on Apple Silicon. Memory is measured for the full package run from model init through video save. RSS alone is not enough for MLX/Metal unified-memory pressure, so the table reports both MLX allocator peak and Darwin physical footprint.
|
| 48 |
+
|
| 49 |
+
| Package | Folder Size | Runtime Precision | Mode | MLX Peak | Physical Footprint Peak | Time | Notes |
|
| 50 |
+
| --- | ---: | --- | --- | ---: | ---: | ---: | --- |
|
| 51 |
+
| Upstream source snapshot | 118 GiB | BF16 runtime from FP32/BF16 source files | release inactive denoiser | 32.99 GiB | 48.90 GiB | 108.31 s | Baseline source-cache run. |
|
| 52 |
+
| BF16 prepared folder | 64 GiB | BF16 | release inactive denoiser | 32.98 GiB | 45.12 GiB | 114.39 s | Output was byte-identical to the source-cache run. |
|
| 53 |
+
| This mixed q8/BF16 folder | 40 GiB | q8 transformer block linears, BF16 sensitive paths and VAE | release inactive denoiser | 20.84 GiB | 31.75 GiB | 110.34 s | Lower usage memory; not byte-identical to BF16 but passed side-by-side validation. |
|
| 54 |
+
| This mixed q8/BF16 folder | 40 GiB | q8 transformer block linears, BF16 sensitive paths and VAE | no denoiser release | 35.19 GiB | 50.55 GiB | 108.10 s | Retains both quantized A14B denoisers through decode. |
|
| 55 |
+
| This mixed q8/BF16 folder | 40 GiB | q8 transformer block linears, BF16 sensitive paths and VAE | low-RAM release | 15.48 GiB | 20.74 GiB | 108.70 s | Lowest measured usage-memory mode. |
|
| 56 |
+
|
| 57 |
+
Within each package/precision, release/no-release/low-RAM outputs were byte-identical. This prepared q8 folder was also byte-identical to runtime `--quantize 8` from the upstream source snapshot. q8 is not byte-identical to BF16, but the validation contact sheet stayed in the same visual family.
|
| 58 |
+
|
| 59 |
+
## Compatibility
|
| 60 |
+
|
| 61 |
+
Requires `mlx-gen >= 0.18.8`.
|
| 62 |
+
|
| 63 |
+
Generated with `mlx-gen 0.18.8`.
|
| 64 |
+
|
| 65 |
+
Use the `mlxgen` command and Python import path for new MLX-Gen projects.
|
| 66 |
+
|
| 67 |
+
## Usage
|
| 68 |
+
|
| 69 |
+
```bash
|
| 70 |
+
python -m pip install -U mlx-gen
|
| 71 |
+
|
| 72 |
+
mlxgen download --model AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit
|
| 73 |
+
|
| 74 |
+
mlxgen generate \
|
| 75 |
+
--model AbstractFramework/wan2.2-t2v-a14b-diffusers-8bit \
|
| 76 |
+
--task text-to-video \
|
| 77 |
+
--prompt "Your video prompt here" \
|
| 78 |
+
--width 1280 \
|
| 79 |
+
--height 720 \
|
| 80 |
+
--frames 81 \
|
| 81 |
+
--steps 40 \
|
| 82 |
+
--guidance 4 \
|
| 83 |
+
--guidance-2 3 \
|
| 84 |
+
--fps 16 \
|
| 85 |
+
--seed 42 \
|
| 86 |
+
--output video.mp4
|
| 87 |
+
```
|
| 88 |
+
|
| 89 |
+
## Attribution
|
| 90 |
+
|
| 91 |
+
MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. This model card is generated by MLX-Gen so derived checkpoints keep that attribution visible.
|
| 92 |
+
|
| 93 |
+
Quantized and contributed by [@lpalbou](https://huggingface.co/lpalbou).
|
model_index.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanPipeline",
|
| 3 |
+
"_diffusers_version": "0.35.0.dev0",
|
| 4 |
+
"boundary_ratio": 0.875,
|
| 5 |
+
"scheduler": [
|
| 6 |
+
"diffusers",
|
| 7 |
+
"UniPCMultistepScheduler"
|
| 8 |
+
],
|
| 9 |
+
"text_encoder": [
|
| 10 |
+
"transformers",
|
| 11 |
+
"UMT5EncoderModel"
|
| 12 |
+
],
|
| 13 |
+
"tokenizer": [
|
| 14 |
+
"transformers",
|
| 15 |
+
"T5TokenizerFast"
|
| 16 |
+
],
|
| 17 |
+
"transformer": [
|
| 18 |
+
"diffusers",
|
| 19 |
+
"WanTransformer3DModel"
|
| 20 |
+
],
|
| 21 |
+
"transformer_2": [
|
| 22 |
+
"diffusers",
|
| 23 |
+
"WanTransformer3DModel"
|
| 24 |
+
],
|
| 25 |
+
"vae": [
|
| 26 |
+
"diffusers",
|
| 27 |
+
"AutoencoderKLWan"
|
| 28 |
+
]
|
| 29 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UniPCMultistepScheduler",
|
| 3 |
+
"_diffusers_version": "0.35.0.dev0",
|
| 4 |
+
"beta_end": 0.02,
|
| 5 |
+
"beta_schedule": "linear",
|
| 6 |
+
"beta_start": 0.0001,
|
| 7 |
+
"disable_corrector": [],
|
| 8 |
+
"dynamic_thresholding_ratio": 0.995,
|
| 9 |
+
"final_sigmas_type": "zero",
|
| 10 |
+
"flow_shift": 3.0,
|
| 11 |
+
"lower_order_final": true,
|
| 12 |
+
"num_train_timesteps": 1000,
|
| 13 |
+
"predict_x0": true,
|
| 14 |
+
"prediction_type": "flow_prediction",
|
| 15 |
+
"rescale_betas_zero_snr": false,
|
| 16 |
+
"sample_max_value": 1.0,
|
| 17 |
+
"solver_order": 2,
|
| 18 |
+
"solver_p": null,
|
| 19 |
+
"solver_type": "bh2",
|
| 20 |
+
"steps_offset": 0,
|
| 21 |
+
"thresholding": false,
|
| 22 |
+
"time_shift_type": "exponential",
|
| 23 |
+
"timestep_spacing": "linspace",
|
| 24 |
+
"trained_betas": null,
|
| 25 |
+
"use_beta_sigmas": false,
|
| 26 |
+
"use_dynamic_shifting": false,
|
| 27 |
+
"use_exponential_sigmas": false,
|
| 28 |
+
"use_flow_sigmas": true,
|
| 29 |
+
"use_karras_sigmas": false
|
| 30 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/umt5-xxl",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"UMT5EncoderModel"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 10240,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 4096,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "umt5",
|
| 20 |
+
"num_decoder_layers": 24,
|
| 21 |
+
"num_heads": 64,
|
| 22 |
+
"num_layers": 24,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"scalable_attention": true,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"tokenizer_class": "T5Tokenizer",
|
| 30 |
+
"torch_dtype": "bfloat16",
|
| 31 |
+
"transformers_version": "4.48.0.dev0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 256384
|
| 34 |
+
}
|
text_encoder/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58
|
| 3 |
+
size 4935812536
|
text_encoder/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d57d948ece4837d850b7a859a4415121d57cacf8b9ee1d4db200c67f592902d7
|
| 3 |
+
size 4983103192
|
text_encoder/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da9ee284e21d1406df708788db1d502d95d75f69faa25cd26151bf8829b7c5f
|
| 3 |
+
size 1442935480
|
text_encoder/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,249 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 11361820672
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 27 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 29 |
+
"encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 33 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 35 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 127 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 128 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 129 |
+
"encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 130 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 131 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 132 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 133 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 134 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 135 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 136 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
| 143 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
| 145 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
| 147 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
| 149 |
+
"encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
| 151 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 177 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 178 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 179 |
+
"encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 180 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 181 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 182 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 183 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 184 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 185 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 186 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 187 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 188 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 189 |
+
"encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 190 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 191 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 192 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 193 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 194 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 195 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 196 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 197 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 198 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 199 |
+
"encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 200 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 201 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 202 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 203 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 204 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 205 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 206 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 207 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 208 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 209 |
+
"encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 210 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 211 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 212 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
| 213 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
| 214 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
| 215 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 224 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"encoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 247 |
+
"shared.weight": "model-00001-of-00003.safetensors"
|
| 248 |
+
}
|
| 249 |
+
}
|
tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e87c960c36d5fbf4e7e76c2469b7eab877be7f8c5992efbf97e44d3123cc6521
|
| 3 |
+
size 16837418
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_ids": 300,
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<extra_id_0>",
|
| 9 |
+
"<extra_id_1>",
|
| 10 |
+
"<extra_id_2>",
|
| 11 |
+
"<extra_id_3>",
|
| 12 |
+
"<extra_id_4>",
|
| 13 |
+
"<extra_id_5>",
|
| 14 |
+
"<extra_id_6>",
|
| 15 |
+
"<extra_id_7>",
|
| 16 |
+
"<extra_id_8>",
|
| 17 |
+
"<extra_id_9>",
|
| 18 |
+
"<extra_id_10>",
|
| 19 |
+
"<extra_id_11>",
|
| 20 |
+
"<extra_id_12>",
|
| 21 |
+
"<extra_id_13>",
|
| 22 |
+
"<extra_id_14>",
|
| 23 |
+
"<extra_id_15>",
|
| 24 |
+
"<extra_id_16>",
|
| 25 |
+
"<extra_id_17>",
|
| 26 |
+
"<extra_id_18>",
|
| 27 |
+
"<extra_id_19>",
|
| 28 |
+
"<extra_id_20>",
|
| 29 |
+
"<extra_id_21>",
|
| 30 |
+
"<extra_id_22>",
|
| 31 |
+
"<extra_id_23>",
|
| 32 |
+
"<extra_id_24>",
|
| 33 |
+
"<extra_id_25>",
|
| 34 |
+
"<extra_id_26>",
|
| 35 |
+
"<extra_id_27>",
|
| 36 |
+
"<extra_id_28>",
|
| 37 |
+
"<extra_id_29>",
|
| 38 |
+
"<extra_id_30>",
|
| 39 |
+
"<extra_id_31>",
|
| 40 |
+
"<extra_id_32>",
|
| 41 |
+
"<extra_id_33>",
|
| 42 |
+
"<extra_id_34>",
|
| 43 |
+
"<extra_id_35>",
|
| 44 |
+
"<extra_id_36>",
|
| 45 |
+
"<extra_id_37>",
|
| 46 |
+
"<extra_id_38>",
|
| 47 |
+
"<extra_id_39>",
|
| 48 |
+
"<extra_id_40>",
|
| 49 |
+
"<extra_id_41>",
|
| 50 |
+
"<extra_id_42>",
|
| 51 |
+
"<extra_id_43>",
|
| 52 |
+
"<extra_id_44>",
|
| 53 |
+
"<extra_id_45>",
|
| 54 |
+
"<extra_id_46>",
|
| 55 |
+
"<extra_id_47>",
|
| 56 |
+
"<extra_id_48>",
|
| 57 |
+
"<extra_id_49>",
|
| 58 |
+
"<extra_id_50>",
|
| 59 |
+
"<extra_id_51>",
|
| 60 |
+
"<extra_id_52>",
|
| 61 |
+
"<extra_id_53>",
|
| 62 |
+
"<extra_id_54>",
|
| 63 |
+
"<extra_id_55>",
|
| 64 |
+
"<extra_id_56>",
|
| 65 |
+
"<extra_id_57>",
|
| 66 |
+
"<extra_id_58>",
|
| 67 |
+
"<extra_id_59>",
|
| 68 |
+
"<extra_id_60>",
|
| 69 |
+
"<extra_id_61>",
|
| 70 |
+
"<extra_id_62>",
|
| 71 |
+
"<extra_id_63>",
|
| 72 |
+
"<extra_id_64>",
|
| 73 |
+
"<extra_id_65>",
|
| 74 |
+
"<extra_id_66>",
|
| 75 |
+
"<extra_id_67>",
|
| 76 |
+
"<extra_id_68>",
|
| 77 |
+
"<extra_id_69>",
|
| 78 |
+
"<extra_id_70>",
|
| 79 |
+
"<extra_id_71>",
|
| 80 |
+
"<extra_id_72>",
|
| 81 |
+
"<extra_id_73>",
|
| 82 |
+
"<extra_id_74>",
|
| 83 |
+
"<extra_id_75>",
|
| 84 |
+
"<extra_id_76>",
|
| 85 |
+
"<extra_id_77>",
|
| 86 |
+
"<extra_id_78>",
|
| 87 |
+
"<extra_id_79>",
|
| 88 |
+
"<extra_id_80>",
|
| 89 |
+
"<extra_id_81>",
|
| 90 |
+
"<extra_id_82>",
|
| 91 |
+
"<extra_id_83>",
|
| 92 |
+
"<extra_id_84>",
|
| 93 |
+
"<extra_id_85>",
|
| 94 |
+
"<extra_id_86>",
|
| 95 |
+
"<extra_id_87>",
|
| 96 |
+
"<extra_id_88>",
|
| 97 |
+
"<extra_id_89>",
|
| 98 |
+
"<extra_id_90>",
|
| 99 |
+
"<extra_id_91>",
|
| 100 |
+
"<extra_id_92>",
|
| 101 |
+
"<extra_id_93>",
|
| 102 |
+
"<extra_id_94>",
|
| 103 |
+
"<extra_id_95>",
|
| 104 |
+
"<extra_id_96>",
|
| 105 |
+
"<extra_id_97>",
|
| 106 |
+
"<extra_id_98>",
|
| 107 |
+
"<extra_id_99>",
|
| 108 |
+
"<extra_id_100>",
|
| 109 |
+
"<extra_id_101>",
|
| 110 |
+
"<extra_id_102>",
|
| 111 |
+
"<extra_id_103>",
|
| 112 |
+
"<extra_id_104>",
|
| 113 |
+
"<extra_id_105>",
|
| 114 |
+
"<extra_id_106>",
|
| 115 |
+
"<extra_id_107>",
|
| 116 |
+
"<extra_id_108>",
|
| 117 |
+
"<extra_id_109>",
|
| 118 |
+
"<extra_id_110>",
|
| 119 |
+
"<extra_id_111>",
|
| 120 |
+
"<extra_id_112>",
|
| 121 |
+
"<extra_id_113>",
|
| 122 |
+
"<extra_id_114>",
|
| 123 |
+
"<extra_id_115>",
|
| 124 |
+
"<extra_id_116>",
|
| 125 |
+
"<extra_id_117>",
|
| 126 |
+
"<extra_id_118>",
|
| 127 |
+
"<extra_id_119>",
|
| 128 |
+
"<extra_id_120>",
|
| 129 |
+
"<extra_id_121>",
|
| 130 |
+
"<extra_id_122>",
|
| 131 |
+
"<extra_id_123>",
|
| 132 |
+
"<extra_id_124>",
|
| 133 |
+
"<extra_id_125>",
|
| 134 |
+
"<extra_id_126>",
|
| 135 |
+
"<extra_id_127>",
|
| 136 |
+
"<extra_id_128>",
|
| 137 |
+
"<extra_id_129>",
|
| 138 |
+
"<extra_id_130>",
|
| 139 |
+
"<extra_id_131>",
|
| 140 |
+
"<extra_id_132>",
|
| 141 |
+
"<extra_id_133>",
|
| 142 |
+
"<extra_id_134>",
|
| 143 |
+
"<extra_id_135>",
|
| 144 |
+
"<extra_id_136>",
|
| 145 |
+
"<extra_id_137>",
|
| 146 |
+
"<extra_id_138>",
|
| 147 |
+
"<extra_id_139>",
|
| 148 |
+
"<extra_id_140>",
|
| 149 |
+
"<extra_id_141>",
|
| 150 |
+
"<extra_id_142>",
|
| 151 |
+
"<extra_id_143>",
|
| 152 |
+
"<extra_id_144>",
|
| 153 |
+
"<extra_id_145>",
|
| 154 |
+
"<extra_id_146>",
|
| 155 |
+
"<extra_id_147>",
|
| 156 |
+
"<extra_id_148>",
|
| 157 |
+
"<extra_id_149>",
|
| 158 |
+
"<extra_id_150>",
|
| 159 |
+
"<extra_id_151>",
|
| 160 |
+
"<extra_id_152>",
|
| 161 |
+
"<extra_id_153>",
|
| 162 |
+
"<extra_id_154>",
|
| 163 |
+
"<extra_id_155>",
|
| 164 |
+
"<extra_id_156>",
|
| 165 |
+
"<extra_id_157>",
|
| 166 |
+
"<extra_id_158>",
|
| 167 |
+
"<extra_id_159>",
|
| 168 |
+
"<extra_id_160>",
|
| 169 |
+
"<extra_id_161>",
|
| 170 |
+
"<extra_id_162>",
|
| 171 |
+
"<extra_id_163>",
|
| 172 |
+
"<extra_id_164>",
|
| 173 |
+
"<extra_id_165>",
|
| 174 |
+
"<extra_id_166>",
|
| 175 |
+
"<extra_id_167>",
|
| 176 |
+
"<extra_id_168>",
|
| 177 |
+
"<extra_id_169>",
|
| 178 |
+
"<extra_id_170>",
|
| 179 |
+
"<extra_id_171>",
|
| 180 |
+
"<extra_id_172>",
|
| 181 |
+
"<extra_id_173>",
|
| 182 |
+
"<extra_id_174>",
|
| 183 |
+
"<extra_id_175>",
|
| 184 |
+
"<extra_id_176>",
|
| 185 |
+
"<extra_id_177>",
|
| 186 |
+
"<extra_id_178>",
|
| 187 |
+
"<extra_id_179>",
|
| 188 |
+
"<extra_id_180>",
|
| 189 |
+
"<extra_id_181>",
|
| 190 |
+
"<extra_id_182>",
|
| 191 |
+
"<extra_id_183>",
|
| 192 |
+
"<extra_id_184>",
|
| 193 |
+
"<extra_id_185>",
|
| 194 |
+
"<extra_id_186>",
|
| 195 |
+
"<extra_id_187>",
|
| 196 |
+
"<extra_id_188>",
|
| 197 |
+
"<extra_id_189>",
|
| 198 |
+
"<extra_id_190>",
|
| 199 |
+
"<extra_id_191>",
|
| 200 |
+
"<extra_id_192>",
|
| 201 |
+
"<extra_id_193>",
|
| 202 |
+
"<extra_id_194>",
|
| 203 |
+
"<extra_id_195>",
|
| 204 |
+
"<extra_id_196>",
|
| 205 |
+
"<extra_id_197>",
|
| 206 |
+
"<extra_id_198>",
|
| 207 |
+
"<extra_id_199>",
|
| 208 |
+
"<extra_id_200>",
|
| 209 |
+
"<extra_id_201>",
|
| 210 |
+
"<extra_id_202>",
|
| 211 |
+
"<extra_id_203>",
|
| 212 |
+
"<extra_id_204>",
|
| 213 |
+
"<extra_id_205>",
|
| 214 |
+
"<extra_id_206>",
|
| 215 |
+
"<extra_id_207>",
|
| 216 |
+
"<extra_id_208>",
|
| 217 |
+
"<extra_id_209>",
|
| 218 |
+
"<extra_id_210>",
|
| 219 |
+
"<extra_id_211>",
|
| 220 |
+
"<extra_id_212>",
|
| 221 |
+
"<extra_id_213>",
|
| 222 |
+
"<extra_id_214>",
|
| 223 |
+
"<extra_id_215>",
|
| 224 |
+
"<extra_id_216>",
|
| 225 |
+
"<extra_id_217>",
|
| 226 |
+
"<extra_id_218>",
|
| 227 |
+
"<extra_id_219>",
|
| 228 |
+
"<extra_id_220>",
|
| 229 |
+
"<extra_id_221>",
|
| 230 |
+
"<extra_id_222>",
|
| 231 |
+
"<extra_id_223>",
|
| 232 |
+
"<extra_id_224>",
|
| 233 |
+
"<extra_id_225>",
|
| 234 |
+
"<extra_id_226>",
|
| 235 |
+
"<extra_id_227>",
|
| 236 |
+
"<extra_id_228>",
|
| 237 |
+
"<extra_id_229>",
|
| 238 |
+
"<extra_id_230>",
|
| 239 |
+
"<extra_id_231>",
|
| 240 |
+
"<extra_id_232>",
|
| 241 |
+
"<extra_id_233>",
|
| 242 |
+
"<extra_id_234>",
|
| 243 |
+
"<extra_id_235>",
|
| 244 |
+
"<extra_id_236>",
|
| 245 |
+
"<extra_id_237>",
|
| 246 |
+
"<extra_id_238>",
|
| 247 |
+
"<extra_id_239>",
|
| 248 |
+
"<extra_id_240>",
|
| 249 |
+
"<extra_id_241>",
|
| 250 |
+
"<extra_id_242>",
|
| 251 |
+
"<extra_id_243>",
|
| 252 |
+
"<extra_id_244>",
|
| 253 |
+
"<extra_id_245>",
|
| 254 |
+
"<extra_id_246>",
|
| 255 |
+
"<extra_id_247>",
|
| 256 |
+
"<extra_id_248>",
|
| 257 |
+
"<extra_id_249>",
|
| 258 |
+
"<extra_id_250>",
|
| 259 |
+
"<extra_id_251>",
|
| 260 |
+
"<extra_id_252>",
|
| 261 |
+
"<extra_id_253>",
|
| 262 |
+
"<extra_id_254>",
|
| 263 |
+
"<extra_id_255>",
|
| 264 |
+
"<extra_id_256>",
|
| 265 |
+
"<extra_id_257>",
|
| 266 |
+
"<extra_id_258>",
|
| 267 |
+
"<extra_id_259>",
|
| 268 |
+
"<extra_id_260>",
|
| 269 |
+
"<extra_id_261>",
|
| 270 |
+
"<extra_id_262>",
|
| 271 |
+
"<extra_id_263>",
|
| 272 |
+
"<extra_id_264>",
|
| 273 |
+
"<extra_id_265>",
|
| 274 |
+
"<extra_id_266>",
|
| 275 |
+
"<extra_id_267>",
|
| 276 |
+
"<extra_id_268>",
|
| 277 |
+
"<extra_id_269>",
|
| 278 |
+
"<extra_id_270>",
|
| 279 |
+
"<extra_id_271>",
|
| 280 |
+
"<extra_id_272>",
|
| 281 |
+
"<extra_id_273>",
|
| 282 |
+
"<extra_id_274>",
|
| 283 |
+
"<extra_id_275>",
|
| 284 |
+
"<extra_id_276>",
|
| 285 |
+
"<extra_id_277>",
|
| 286 |
+
"<extra_id_278>",
|
| 287 |
+
"<extra_id_279>",
|
| 288 |
+
"<extra_id_280>",
|
| 289 |
+
"<extra_id_281>",
|
| 290 |
+
"<extra_id_282>",
|
| 291 |
+
"<extra_id_283>",
|
| 292 |
+
"<extra_id_284>",
|
| 293 |
+
"<extra_id_285>",
|
| 294 |
+
"<extra_id_286>",
|
| 295 |
+
"<extra_id_287>",
|
| 296 |
+
"<extra_id_288>",
|
| 297 |
+
"<extra_id_289>",
|
| 298 |
+
"<extra_id_290>",
|
| 299 |
+
"<extra_id_291>",
|
| 300 |
+
"<extra_id_292>",
|
| 301 |
+
"<extra_id_293>",
|
| 302 |
+
"<extra_id_294>",
|
| 303 |
+
"<extra_id_295>",
|
| 304 |
+
"<extra_id_296>",
|
| 305 |
+
"<extra_id_297>",
|
| 306 |
+
"<extra_id_298>",
|
| 307 |
+
"<extra_id_299>"
|
| 308 |
+
],
|
| 309 |
+
"is_local": true,
|
| 310 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 311 |
+
"model_specific_special_tokens": {},
|
| 312 |
+
"pad_token": "<pad>",
|
| 313 |
+
"sp_model_kwargs": {},
|
| 314 |
+
"spaces_between_special_tokens": false,
|
| 315 |
+
"tokenizer_class": "T5Tokenizer",
|
| 316 |
+
"unk_token": "<unk>"
|
| 317 |
+
}
|
transformer/0.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d324244b04b73bd63a5e41775a9a5fc0e38a0fdc6f6f641d274496fed8d8d727
|
| 3 |
+
size 2126914156
|
transformer/1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df5419e4f564780aaa48b01874bae29a765c3df5466f5d8878fd2b85537f6cd9
|
| 3 |
+
size 2129375449
|
transformer/2.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd1774082f5db81dca8f8ed514c241e0ab58f3b434b108c579ab72c9298cc4be
|
| 3 |
+
size 2109848506
|
transformer/3.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b85b62cfbe121c9ba895d83e71fb22df7f793f907ba6d462da7d86e000aa7294
|
| 3 |
+
size 2137714721
|
transformer/4.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c966f65563f26fcce793a4cf823949926f987a60ed8ddb837eddff91f133642
|
| 3 |
+
size 2129375671
|
transformer/5.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43cccf0b11fc18715f05c530d2cfe8e4ee6c1c1e7c8fbc57f13d02d6c535468d
|
| 3 |
+
size 2081985022
|
transformer/6.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:401c3d202660a8ab6d75d119cf1b7a019c94e9aed131b478a7d67cc5d71e5747
|
| 3 |
+
size 2137714713
|
transformer/7.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3684a00b35ab9db7a5c103704ef99943a12d60ad18ad9e2932d126f40afd0abc
|
| 3 |
+
size 552561394
|
transformer/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer_2/0.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2732c943575c11fef937956a9e8400ced38374295954b58fbc5a1af01d32f986
|
| 3 |
+
size 2126914156
|
transformer_2/1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e2f216038257ac1b3a21def6062756d862ce266fd571f1c4a9cd03ca1b7e0b7
|
| 3 |
+
size 2129375449
|
transformer_2/2.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94647aeaca6371b650257c9879bf1d16cb273f4b158176ab1169a93703adad0
|
| 3 |
+
size 2109848506
|
transformer_2/3.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:544ac869de8cf8205875ca1677617ec28f300b440cb8b414a8c868bc2d45b1e4
|
| 3 |
+
size 2137714721
|
transformer_2/4.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0efb68e19c4b89ad3d822c4d1d5c8971f3be063da25785cdf98f4ef3d23973c3
|
| 3 |
+
size 2129375671
|
transformer_2/5.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f50af08070a793cca64ade0eb3209d928511fa524e229eeb090cee13f62d1af4
|
| 3 |
+
size 2081985022
|
transformer_2/6.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68d30462066067fa5e8e8c0386f56257e71a721303e6575e7395af8e7e0c68c3
|
| 3 |
+
size 2137714713
|
transformer_2/7.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc7a2a4ef35f0d608768caf516d2a0dd3b2d8da782b6598294adeb5272ecaed1
|
| 3 |
+
size 552561394
|
transformer_2/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vae/0.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:039ca54426d7cbfb4ecf852f06b0d943c2450f34a6c92c357824c69d8449587f
|
| 3 |
+
size 253807817
|
vae/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"quantization_level": "8",
|
| 4 |
+
"mflux_version": "0.18.8"
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"encoder.conv_in.conv3d.weight": "0.safetensors",
|
| 8 |
+
"encoder.conv_in.conv3d.bias": "0.safetensors",
|
| 9 |
+
"encoder.down_blocks.0.norm1.weight": "0.safetensors",
|
| 10 |
+
"encoder.down_blocks.0.conv1.conv3d.weight": "0.safetensors",
|
| 11 |
+
"encoder.down_blocks.0.conv1.conv3d.bias": "0.safetensors",
|
| 12 |
+
"encoder.down_blocks.0.norm2.weight": "0.safetensors",
|
| 13 |
+
"encoder.down_blocks.0.conv2.conv3d.weight": "0.safetensors",
|
| 14 |
+
"encoder.down_blocks.0.conv2.conv3d.bias": "0.safetensors",
|
| 15 |
+
"encoder.down_blocks.1.norm1.weight": "0.safetensors",
|
| 16 |
+
"encoder.down_blocks.1.conv1.conv3d.weight": "0.safetensors",
|
| 17 |
+
"encoder.down_blocks.1.conv1.conv3d.bias": "0.safetensors",
|
| 18 |
+
"encoder.down_blocks.1.norm2.weight": "0.safetensors",
|
| 19 |
+
"encoder.down_blocks.1.conv2.conv3d.weight": "0.safetensors",
|
| 20 |
+
"encoder.down_blocks.1.conv2.conv3d.bias": "0.safetensors",
|
| 21 |
+
"encoder.down_blocks.2.resample_conv.weight": "0.safetensors",
|
| 22 |
+
"encoder.down_blocks.2.resample_conv.bias": "0.safetensors",
|
| 23 |
+
"encoder.down_blocks.3.norm1.weight": "0.safetensors",
|
| 24 |
+
"encoder.down_blocks.3.conv1.conv3d.weight": "0.safetensors",
|
| 25 |
+
"encoder.down_blocks.3.conv1.conv3d.bias": "0.safetensors",
|
| 26 |
+
"encoder.down_blocks.3.norm2.weight": "0.safetensors",
|
| 27 |
+
"encoder.down_blocks.3.conv2.conv3d.weight": "0.safetensors",
|
| 28 |
+
"encoder.down_blocks.3.conv2.conv3d.bias": "0.safetensors",
|
| 29 |
+
"encoder.down_blocks.3.conv_shortcut.conv3d.weight": "0.safetensors",
|
| 30 |
+
"encoder.down_blocks.3.conv_shortcut.conv3d.bias": "0.safetensors",
|
| 31 |
+
"encoder.down_blocks.4.norm1.weight": "0.safetensors",
|
| 32 |
+
"encoder.down_blocks.4.conv1.conv3d.weight": "0.safetensors",
|
| 33 |
+
"encoder.down_blocks.4.conv1.conv3d.bias": "0.safetensors",
|
| 34 |
+
"encoder.down_blocks.4.norm2.weight": "0.safetensors",
|
| 35 |
+
"encoder.down_blocks.4.conv2.conv3d.weight": "0.safetensors",
|
| 36 |
+
"encoder.down_blocks.4.conv2.conv3d.bias": "0.safetensors",
|
| 37 |
+
"encoder.down_blocks.5.resample_conv.weight": "0.safetensors",
|
| 38 |
+
"encoder.down_blocks.5.resample_conv.bias": "0.safetensors",
|
| 39 |
+
"encoder.down_blocks.5.time_conv.conv3d.weight": "0.safetensors",
|
| 40 |
+
"encoder.down_blocks.5.time_conv.conv3d.bias": "0.safetensors",
|
| 41 |
+
"encoder.down_blocks.6.norm1.weight": "0.safetensors",
|
| 42 |
+
"encoder.down_blocks.6.conv1.conv3d.weight": "0.safetensors",
|
| 43 |
+
"encoder.down_blocks.6.conv1.conv3d.bias": "0.safetensors",
|
| 44 |
+
"encoder.down_blocks.6.norm2.weight": "0.safetensors",
|
| 45 |
+
"encoder.down_blocks.6.conv2.conv3d.weight": "0.safetensors",
|
| 46 |
+
"encoder.down_blocks.6.conv2.conv3d.bias": "0.safetensors",
|
| 47 |
+
"encoder.down_blocks.6.conv_shortcut.conv3d.weight": "0.safetensors",
|
| 48 |
+
"encoder.down_blocks.6.conv_shortcut.conv3d.bias": "0.safetensors",
|
| 49 |
+
"encoder.down_blocks.7.norm1.weight": "0.safetensors",
|
| 50 |
+
"encoder.down_blocks.7.conv1.conv3d.weight": "0.safetensors",
|
| 51 |
+
"encoder.down_blocks.7.conv1.conv3d.bias": "0.safetensors",
|
| 52 |
+
"encoder.down_blocks.7.norm2.weight": "0.safetensors",
|
| 53 |
+
"encoder.down_blocks.7.conv2.conv3d.weight": "0.safetensors",
|
| 54 |
+
"encoder.down_blocks.7.conv2.conv3d.bias": "0.safetensors",
|
| 55 |
+
"encoder.down_blocks.8.resample_conv.weight": "0.safetensors",
|
| 56 |
+
"encoder.down_blocks.8.resample_conv.bias": "0.safetensors",
|
| 57 |
+
"encoder.down_blocks.8.time_conv.conv3d.weight": "0.safetensors",
|
| 58 |
+
"encoder.down_blocks.8.time_conv.conv3d.bias": "0.safetensors",
|
| 59 |
+
"encoder.down_blocks.9.norm1.weight": "0.safetensors",
|
| 60 |
+
"encoder.down_blocks.9.conv1.conv3d.weight": "0.safetensors",
|
| 61 |
+
"encoder.down_blocks.9.conv1.conv3d.bias": "0.safetensors",
|
| 62 |
+
"encoder.down_blocks.9.norm2.weight": "0.safetensors",
|
| 63 |
+
"encoder.down_blocks.9.conv2.conv3d.weight": "0.safetensors",
|
| 64 |
+
"encoder.down_blocks.9.conv2.conv3d.bias": "0.safetensors",
|
| 65 |
+
"encoder.down_blocks.10.norm1.weight": "0.safetensors",
|
| 66 |
+
"encoder.down_blocks.10.conv1.conv3d.weight": "0.safetensors",
|
| 67 |
+
"encoder.down_blocks.10.conv1.conv3d.bias": "0.safetensors",
|
| 68 |
+
"encoder.down_blocks.10.norm2.weight": "0.safetensors",
|
| 69 |
+
"encoder.down_blocks.10.conv2.conv3d.weight": "0.safetensors",
|
| 70 |
+
"encoder.down_blocks.10.conv2.conv3d.bias": "0.safetensors",
|
| 71 |
+
"encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
|
| 72 |
+
"encoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 73 |
+
"encoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 74 |
+
"encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
|
| 75 |
+
"encoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 76 |
+
"encoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 77 |
+
"encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
|
| 78 |
+
"encoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 79 |
+
"encoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 80 |
+
"encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
|
| 81 |
+
"encoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 82 |
+
"encoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 83 |
+
"encoder.mid_block.attentions.0.norm.weight": "0.safetensors",
|
| 84 |
+
"encoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
|
| 85 |
+
"encoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
|
| 86 |
+
"encoder.mid_block.attentions.0.proj.weight": "0.safetensors",
|
| 87 |
+
"encoder.mid_block.attentions.0.proj.bias": "0.safetensors",
|
| 88 |
+
"encoder.norm_out.weight": "0.safetensors",
|
| 89 |
+
"encoder.conv_out.conv3d.weight": "0.safetensors",
|
| 90 |
+
"encoder.conv_out.conv3d.bias": "0.safetensors",
|
| 91 |
+
"decoder.conv_in.conv3d.weight": "0.safetensors",
|
| 92 |
+
"decoder.conv_in.conv3d.bias": "0.safetensors",
|
| 93 |
+
"decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
|
| 94 |
+
"decoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 95 |
+
"decoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 96 |
+
"decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
|
| 97 |
+
"decoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 98 |
+
"decoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 99 |
+
"decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
|
| 100 |
+
"decoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 101 |
+
"decoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 102 |
+
"decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
|
| 103 |
+
"decoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 104 |
+
"decoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 105 |
+
"decoder.mid_block.attentions.0.norm.weight": "0.safetensors",
|
| 106 |
+
"decoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
|
| 107 |
+
"decoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
|
| 108 |
+
"decoder.mid_block.attentions.0.proj.weight": "0.safetensors",
|
| 109 |
+
"decoder.mid_block.attentions.0.proj.bias": "0.safetensors",
|
| 110 |
+
"decoder.up_blocks.0.resnets.0.norm1.weight": "0.safetensors",
|
| 111 |
+
"decoder.up_blocks.0.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 112 |
+
"decoder.up_blocks.0.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 113 |
+
"decoder.up_blocks.0.resnets.0.norm2.weight": "0.safetensors",
|
| 114 |
+
"decoder.up_blocks.0.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 115 |
+
"decoder.up_blocks.0.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 116 |
+
"decoder.up_blocks.0.resnets.1.norm1.weight": "0.safetensors",
|
| 117 |
+
"decoder.up_blocks.0.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 118 |
+
"decoder.up_blocks.0.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 119 |
+
"decoder.up_blocks.0.resnets.1.norm2.weight": "0.safetensors",
|
| 120 |
+
"decoder.up_blocks.0.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 121 |
+
"decoder.up_blocks.0.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 122 |
+
"decoder.up_blocks.0.resnets.2.norm1.weight": "0.safetensors",
|
| 123 |
+
"decoder.up_blocks.0.resnets.2.conv1.conv3d.weight": "0.safetensors",
|
| 124 |
+
"decoder.up_blocks.0.resnets.2.conv1.conv3d.bias": "0.safetensors",
|
| 125 |
+
"decoder.up_blocks.0.resnets.2.norm2.weight": "0.safetensors",
|
| 126 |
+
"decoder.up_blocks.0.resnets.2.conv2.conv3d.weight": "0.safetensors",
|
| 127 |
+
"decoder.up_blocks.0.resnets.2.conv2.conv3d.bias": "0.safetensors",
|
| 128 |
+
"decoder.up_blocks.0.upsamplers.0.time_conv.conv3d.weight": "0.safetensors",
|
| 129 |
+
"decoder.up_blocks.0.upsamplers.0.time_conv.conv3d.bias": "0.safetensors",
|
| 130 |
+
"decoder.up_blocks.0.upsamplers.0.resample_conv.weight": "0.safetensors",
|
| 131 |
+
"decoder.up_blocks.0.upsamplers.0.resample_conv.bias": "0.safetensors",
|
| 132 |
+
"decoder.up_blocks.1.resnets.0.norm1.weight": "0.safetensors",
|
| 133 |
+
"decoder.up_blocks.1.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 134 |
+
"decoder.up_blocks.1.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 135 |
+
"decoder.up_blocks.1.resnets.0.norm2.weight": "0.safetensors",
|
| 136 |
+
"decoder.up_blocks.1.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 137 |
+
"decoder.up_blocks.1.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 138 |
+
"decoder.up_blocks.1.resnets.0.conv_shortcut.conv3d.weight": "0.safetensors",
|
| 139 |
+
"decoder.up_blocks.1.resnets.0.conv_shortcut.conv3d.bias": "0.safetensors",
|
| 140 |
+
"decoder.up_blocks.1.resnets.1.norm1.weight": "0.safetensors",
|
| 141 |
+
"decoder.up_blocks.1.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 142 |
+
"decoder.up_blocks.1.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 143 |
+
"decoder.up_blocks.1.resnets.1.norm2.weight": "0.safetensors",
|
| 144 |
+
"decoder.up_blocks.1.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 145 |
+
"decoder.up_blocks.1.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 146 |
+
"decoder.up_blocks.1.resnets.2.norm1.weight": "0.safetensors",
|
| 147 |
+
"decoder.up_blocks.1.resnets.2.conv1.conv3d.weight": "0.safetensors",
|
| 148 |
+
"decoder.up_blocks.1.resnets.2.conv1.conv3d.bias": "0.safetensors",
|
| 149 |
+
"decoder.up_blocks.1.resnets.2.norm2.weight": "0.safetensors",
|
| 150 |
+
"decoder.up_blocks.1.resnets.2.conv2.conv3d.weight": "0.safetensors",
|
| 151 |
+
"decoder.up_blocks.1.resnets.2.conv2.conv3d.bias": "0.safetensors",
|
| 152 |
+
"decoder.up_blocks.1.upsamplers.0.time_conv.conv3d.weight": "0.safetensors",
|
| 153 |
+
"decoder.up_blocks.1.upsamplers.0.time_conv.conv3d.bias": "0.safetensors",
|
| 154 |
+
"decoder.up_blocks.1.upsamplers.0.resample_conv.weight": "0.safetensors",
|
| 155 |
+
"decoder.up_blocks.1.upsamplers.0.resample_conv.bias": "0.safetensors",
|
| 156 |
+
"decoder.up_blocks.2.resnets.0.norm1.weight": "0.safetensors",
|
| 157 |
+
"decoder.up_blocks.2.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 158 |
+
"decoder.up_blocks.2.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 159 |
+
"decoder.up_blocks.2.resnets.0.norm2.weight": "0.safetensors",
|
| 160 |
+
"decoder.up_blocks.2.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 161 |
+
"decoder.up_blocks.2.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 162 |
+
"decoder.up_blocks.2.resnets.1.norm1.weight": "0.safetensors",
|
| 163 |
+
"decoder.up_blocks.2.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 164 |
+
"decoder.up_blocks.2.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 165 |
+
"decoder.up_blocks.2.resnets.1.norm2.weight": "0.safetensors",
|
| 166 |
+
"decoder.up_blocks.2.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 167 |
+
"decoder.up_blocks.2.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 168 |
+
"decoder.up_blocks.2.resnets.2.norm1.weight": "0.safetensors",
|
| 169 |
+
"decoder.up_blocks.2.resnets.2.conv1.conv3d.weight": "0.safetensors",
|
| 170 |
+
"decoder.up_blocks.2.resnets.2.conv1.conv3d.bias": "0.safetensors",
|
| 171 |
+
"decoder.up_blocks.2.resnets.2.norm2.weight": "0.safetensors",
|
| 172 |
+
"decoder.up_blocks.2.resnets.2.conv2.conv3d.weight": "0.safetensors",
|
| 173 |
+
"decoder.up_blocks.2.resnets.2.conv2.conv3d.bias": "0.safetensors",
|
| 174 |
+
"decoder.up_blocks.2.upsamplers.0.resample_conv.weight": "0.safetensors",
|
| 175 |
+
"decoder.up_blocks.2.upsamplers.0.resample_conv.bias": "0.safetensors",
|
| 176 |
+
"decoder.up_blocks.3.resnets.0.norm1.weight": "0.safetensors",
|
| 177 |
+
"decoder.up_blocks.3.resnets.0.conv1.conv3d.weight": "0.safetensors",
|
| 178 |
+
"decoder.up_blocks.3.resnets.0.conv1.conv3d.bias": "0.safetensors",
|
| 179 |
+
"decoder.up_blocks.3.resnets.0.norm2.weight": "0.safetensors",
|
| 180 |
+
"decoder.up_blocks.3.resnets.0.conv2.conv3d.weight": "0.safetensors",
|
| 181 |
+
"decoder.up_blocks.3.resnets.0.conv2.conv3d.bias": "0.safetensors",
|
| 182 |
+
"decoder.up_blocks.3.resnets.1.norm1.weight": "0.safetensors",
|
| 183 |
+
"decoder.up_blocks.3.resnets.1.conv1.conv3d.weight": "0.safetensors",
|
| 184 |
+
"decoder.up_blocks.3.resnets.1.conv1.conv3d.bias": "0.safetensors",
|
| 185 |
+
"decoder.up_blocks.3.resnets.1.norm2.weight": "0.safetensors",
|
| 186 |
+
"decoder.up_blocks.3.resnets.1.conv2.conv3d.weight": "0.safetensors",
|
| 187 |
+
"decoder.up_blocks.3.resnets.1.conv2.conv3d.bias": "0.safetensors",
|
| 188 |
+
"decoder.up_blocks.3.resnets.2.norm1.weight": "0.safetensors",
|
| 189 |
+
"decoder.up_blocks.3.resnets.2.conv1.conv3d.weight": "0.safetensors",
|
| 190 |
+
"decoder.up_blocks.3.resnets.2.conv1.conv3d.bias": "0.safetensors",
|
| 191 |
+
"decoder.up_blocks.3.resnets.2.norm2.weight": "0.safetensors",
|
| 192 |
+
"decoder.up_blocks.3.resnets.2.conv2.conv3d.weight": "0.safetensors",
|
| 193 |
+
"decoder.up_blocks.3.resnets.2.conv2.conv3d.bias": "0.safetensors",
|
| 194 |
+
"decoder.norm_out.weight": "0.safetensors",
|
| 195 |
+
"decoder.conv_out.conv3d.weight": "0.safetensors",
|
| 196 |
+
"decoder.conv_out.conv3d.bias": "0.safetensors",
|
| 197 |
+
"quant_conv.conv3d.weight": "0.safetensors",
|
| 198 |
+
"quant_conv.conv3d.bias": "0.safetensors",
|
| 199 |
+
"post_quant_conv.conv3d.weight": "0.safetensors",
|
| 200 |
+
"post_quant_conv.conv3d.bias": "0.safetensors"
|
| 201 |
+
}
|
| 202 |
+
}
|