Add files using upload-large-folder tool
Browse files- Qwen2.5-Coder-32B-Instruct/model-00001-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00002-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00003-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00004-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00005-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00006-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00007-of-00014.safetensors +3 -0
- Qwen2.5-Coder-32B-Instruct/model-00008-of-00014.safetensors +3 -0
- evo-1-8k-base/evo-1-8k-base/.gitattributes +35 -0
- evo-1-8k-base/evo-1-8k-base/README.md +101 -0
- evo-1-8k-base/evo-1-8k-base/config.json +90 -0
- evo-1-8k-base/evo-1-8k-base/generation_config.json +4 -0
- evo-1-8k-base/evo-1-8k-base/model-00002-of-00003.safetensors +3 -0
- evo-1-8k-base/evo-1-8k-base/model-00003-of-00003.safetensors +3 -0
- evo-1-8k-base/evo-1-8k-base/model.safetensors.index.json +445 -0
- evo-1-8k-base/evo-1-8k-base/special_tokens_map.json +1 -0
- evo-1-8k-base/evo-1-8k-base/tokenizer_config.json +14 -0
- evo-1-8k-base/pytorch_model.bin.index.json +446 -0
- evo-1-8k-base/special_tokens_map.json +1 -0
- evo-1-8k-base/tokenizer_config.json +14 -0
Qwen2.5-Coder-32B-Instruct/model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5746929d771eb06ba0105671a2018dca3c648d4664ca5a5ce2077df82fabad92
|
| 3 |
+
size 4891730992
|
Qwen2.5-Coder-32B-Instruct/model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12aaad653a85d7212a9cc7722937fff7b2bd060ab8522399b4a74d2bf736df8d
|
| 3 |
+
size 4876059352
|
Qwen2.5-Coder-32B-Instruct/model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bac433064b2c29f3e2a891539993b74b7a1da5b0a78c900b2e22fc20fe66059
|
| 3 |
+
size 4876059384
|
Qwen2.5-Coder-32B-Instruct/model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e859e864a61c45dc2e38650359540e5f35f09d4a6993ef66d7274760e7d1905
|
| 3 |
+
size 4876059416
|
Qwen2.5-Coder-32B-Instruct/model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57000579cf2e87cd575333288c25588a45816fc406ace74a52efed1e7bc910d5
|
| 3 |
+
size 4876059416
|
Qwen2.5-Coder-32B-Instruct/model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72dd80465092fad2665c9705332efa99c20b9fb22ad1944e7fe7429a222ede42
|
| 3 |
+
size 4876059416
|
Qwen2.5-Coder-32B-Instruct/model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b91130f8049d3446221000a1d44cdf7bd344f01a2b5843f9bb81ac8193beeae8
|
| 3 |
+
size 4876059416
|
Qwen2.5-Coder-32B-Instruct/model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:522db6c67390557f2964a4a0094a463a067c91992be164b6e141aa1267a225e5
|
| 3 |
+
size 4876059416
|
evo-1-8k-base/evo-1-8k-base/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
evo-1-8k-base/evo-1-8k-base/README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- stripedhyena
|
| 5 |
+
- long context
|
| 6 |
+
- deep signal processing
|
| 7 |
+
- hybrid
|
| 8 |
+
- biology
|
| 9 |
+
- genomics
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Evo-1 (Phase 1)
|
| 14 |
+
|
| 15 |
+
<p align="center">
|
| 16 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/62a1306bbe7fa896d2c8de44/JoEHcvLTUlHoMcgh3mmAz.png" width="70%" />
|
| 17 |
+
</p>
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
### News
|
| 21 |
+
|
| 22 |
+
We identified and fixed an issue related to a wrong permutation of some projections, which affects generation quality. To use the new model revision, please load as follows:
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
config = AutoConfig.from_pretrained(model_name, trust_remote_code=True, revision="1.1_fix")
|
| 26 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 27 |
+
model_name,
|
| 28 |
+
config=config,
|
| 29 |
+
trust_remote_code=True,
|
| 30 |
+
revision="1.1_fix"
|
| 31 |
+
)
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
### About
|
| 35 |
+
|
| 36 |
+
Evo is a biological foundation model capable of long-context modeling and design.
|
| 37 |
+
|
| 38 |
+
Evo uses the [StripedHyena architecture](https://github.com/togethercomputer/stripedhyena) to enable modeling of sequences at a single-nucleotide, byte-level resolution with near-linear scaling of compute and memory relative to context length.
|
| 39 |
+
Evo has 7 billion parameters and is trained on OpenGenome, a prokaryotic whole-genome dataset containing ~300 billion tokens.
|
| 40 |
+
|
| 41 |
+
Technical details about Evo can be found in our preprint and our accompanying blog posts. Evo was collaboratively developed by the [Arc Institute](https://arcinstitute.org/) and TogetherAI.
|
| 42 |
+
|
| 43 |
+
As part of our commitment to open science, we release **weights of 15 intermediate pretraining checkpoints** for phase 1 and phase 2 of pretraining. The checkpoints are available as branches of the corresponding HuggingFace repository.
|
| 44 |
+
|
| 45 |
+
**Evo-1 (Phase 1)** is our first model in the Evo family, trained at a context length of 8k.
|
| 46 |
+
|
| 47 |
+
| Checkpoint Name | Description |
|
| 48 |
+
|----------------------------------------|-------------|
|
| 49 |
+
| `evo-1-8k-base` | A model pretrained with 8,192 context. We use this model as the base model for molecular-scale finetuning tasks. |
|
| 50 |
+
| `evo-1-131k-base` | A model pretrained with 131,072 context using `evo-1-8k-base` as the initialization. We use this model to reason about and generate sequences at the genome scale. |
|
| 51 |
+
|
| 52 |
+
### Model Architecture
|
| 53 |
+
|
| 54 |
+
StripedHyena is a deep signal processing, hybrid architecture composed of multi-head attention and gated convolutions arranged in [Hyena](https://arxiv.org/abs/2302.10866) blocks, improving over decoder-only Transformers.
|
| 55 |
+
|
| 56 |
+
StripedHyena is designed to leverage the specialization of each of its layer classes, with Hyena layers implementing the bulk of the computation required for sequence processing and attention layers supplementing the ability to perform targeted pattern recall.
|
| 57 |
+
|
| 58 |
+
Some highlights of the architecture:
|
| 59 |
+
- **Efficient autoregressive generation** via a recurrent mode (>500k generation with a single 80GB GPU)
|
| 60 |
+
- **Significantly faster training and finetuning** at long context (>3x at 131k)
|
| 61 |
+
- **Improved scaling laws over state-of-the-art architectures** (e.g., Transformer++) on both natural language and biological sequences.
|
| 62 |
+
- **Robust to training beyond the compute-optimal frontier** e.g., training way beyond Chinchilla-optimal token amounts (see preprint for details -- more details to come)
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### How to use Evo
|
| 66 |
+
|
| 67 |
+
Example usage is provided in the [standalone repo](https://github.com/evo-design/evo).
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
#### Parametrization for Inference and Finetuning
|
| 71 |
+
|
| 72 |
+
One of the advantages of deep signal processing models is their flexibility. Different parametrizations of convolutions can be used depending on the memory, expressivity and causality requirements of pretraining, finetuning or inference workloads.
|
| 73 |
+
|
| 74 |
+
The main classes are:
|
| 75 |
+
- Modal canonical: unconstrained poles ([reference](https://arxiv.org/pdf/2203.14343.pdf), [reference](https://arxiv.org/abs/2310.18780)), or constrained poles ([reference](https://arxiv.org/abs/2206.11893), [reference](https://arxiv.org/pdf/2303.06349.pdf)).
|
| 76 |
+
- Companion canonical / rational: TBA.
|
| 77 |
+
- Hypernetworks: hypernetwork ([reference](https://arxiv.org/abs/2102.02611)), modulated hypernetwork ([reference](https://arxiv.org/abs/2302.10866)).
|
| 78 |
+
- Explicit: modulated explicit ([reference](https://arxiv.org/pdf/2210.09298.pdf)).
|
| 79 |
+
|
| 80 |
+
StripedHyena is a mixed precision model. Make sure to keep your `poles` and `residues` in `float32` precision, especially for longer prompts or training.
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Disclaimer
|
| 85 |
+
|
| 86 |
+
To use StripedHyena outside of the playground, you will need to install custom kernels. Please follow the instructions from the [standalone repository](https://github.com/togethercomputer/stripedhyena).
|
| 87 |
+
|
| 88 |
+
## Cite
|
| 89 |
+
|
| 90 |
+
```
|
| 91 |
+
@article{nguyen2024sequence,
|
| 92 |
+
author = {Eric Nguyen and Michael Poli and Matthew G. Durrant and Brian Kang and Dhruva Katrekar and David B. Li and Liam J. Bartie and Armin W. Thomas and Samuel H. King and Garyk Brixi and Jeremy Sullivan and Madelena Y. Ng and Ashley Lewis and Aaron Lou and Stefano Ermon and Stephen A. Baccus and Tina Hernandez-Boussard and Christopher Ré and Patrick D. Hsu and Brian L. Hie },
|
| 93 |
+
title = {Sequence modeling and design from molecular to genome scale with Evo},
|
| 94 |
+
journal = {Science},
|
| 95 |
+
volume = {386},
|
| 96 |
+
number = {6723},
|
| 97 |
+
pages = {eado9336},
|
| 98 |
+
year = {2024},
|
| 99 |
+
doi = {10.1126/science.ado9336},
|
| 100 |
+
URL = {https://www.science.org/doi/abs/10.1126/science.ado9336},
|
| 101 |
+
```
|
evo-1-8k-base/evo-1-8k-base/config.json
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "1cc23830f62c268082475776fb449af8428eb703",
|
| 3 |
+
"_name_or_path": "togethercomputer/evo-1-131k-base",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"StripedHyenaModelForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_layer_idxs": [
|
| 8 |
+
8,
|
| 9 |
+
16,
|
| 10 |
+
24
|
| 11 |
+
],
|
| 12 |
+
"auto_map": {
|
| 13 |
+
"AutoConfig": "togethercomputer/evo-1-131k-base--configuration_hyena.StripedHyenaConfig",
|
| 14 |
+
"AutoModelForCausalLM": "togethercomputer/evo-1-131k-base--modeling_hyena.StripedHyenaModelForCausalLM",
|
| 15 |
+
"AutoTokenizer": [
|
| 16 |
+
"togethercomputer/evo-1-131k-base--tokenizer.ByteTokenizer",
|
| 17 |
+
null
|
| 18 |
+
]
|
| 19 |
+
},
|
| 20 |
+
"column_split": false,
|
| 21 |
+
"column_split_hyena": true,
|
| 22 |
+
"eps": 1e-06,
|
| 23 |
+
"final_norm": true,
|
| 24 |
+
"hidden_size": 4096,
|
| 25 |
+
"hyena_filter_groups": 1,
|
| 26 |
+
"hyena_layer_idxs": [
|
| 27 |
+
0,
|
| 28 |
+
1,
|
| 29 |
+
2,
|
| 30 |
+
3,
|
| 31 |
+
4,
|
| 32 |
+
5,
|
| 33 |
+
6,
|
| 34 |
+
7,
|
| 35 |
+
9,
|
| 36 |
+
10,
|
| 37 |
+
11,
|
| 38 |
+
12,
|
| 39 |
+
13,
|
| 40 |
+
14,
|
| 41 |
+
15,
|
| 42 |
+
17,
|
| 43 |
+
18,
|
| 44 |
+
19,
|
| 45 |
+
20,
|
| 46 |
+
21,
|
| 47 |
+
22,
|
| 48 |
+
23,
|
| 49 |
+
25,
|
| 50 |
+
26,
|
| 51 |
+
27,
|
| 52 |
+
28,
|
| 53 |
+
29,
|
| 54 |
+
30,
|
| 55 |
+
31
|
| 56 |
+
],
|
| 57 |
+
"inference_mode": false,
|
| 58 |
+
"inner_mlp_size": 10928,
|
| 59 |
+
"log_intermediate_values": false,
|
| 60 |
+
"make_vocab_size_divisible_by": 8,
|
| 61 |
+
"max_seqlen": 8192,
|
| 62 |
+
"mha_out_proj_bias": true,
|
| 63 |
+
"mlp_activation": "gelu",
|
| 64 |
+
"model_parallel_size": 1,
|
| 65 |
+
"model_type": "stripedhyena",
|
| 66 |
+
"num_attention_heads": 32,
|
| 67 |
+
"num_filters": 4096,
|
| 68 |
+
"num_layers": 32,
|
| 69 |
+
"pipe_parallel_size": 1,
|
| 70 |
+
"prefill_style": "fft",
|
| 71 |
+
"proj_groups": 1,
|
| 72 |
+
"qkv_proj_bias": true,
|
| 73 |
+
"rotary_emb_base": 10000,
|
| 74 |
+
"rotary_emb_scaling_factor": 1,
|
| 75 |
+
"short_filter_bias": true,
|
| 76 |
+
"short_filter_length": 3,
|
| 77 |
+
"smeared_gqa": false,
|
| 78 |
+
"split_k0": true,
|
| 79 |
+
"state_size": 8,
|
| 80 |
+
"tie_embeddings": true,
|
| 81 |
+
"torch_dtype": "bfloat16",
|
| 82 |
+
"transformers_version": null,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_flash_attn": true,
|
| 85 |
+
"use_flash_depthwise": false,
|
| 86 |
+
"use_flash_rmsnorm": false,
|
| 87 |
+
"use_flashfft": false,
|
| 88 |
+
"use_interpolated_rotary_pos_emb": false,
|
| 89 |
+
"vocab_size": 512
|
| 90 |
+
}
|
evo-1-8k-base/evo-1-8k-base/generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.36.2"
|
| 4 |
+
}
|
evo-1-8k-base/evo-1-8k-base/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf18e9010465bff1def520ef5f6124dffde1b36eb2a3359fb6a995afbae284c0
|
| 3 |
+
size 4929849248
|
evo-1-8k-base/evo-1-8k-base/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d054d7f3ef4286da9e51045016de044738f4e66da332576f6d292c7965ecc4
|
| 3 |
+
size 3003304856
|
evo-1-8k-base/evo-1-8k-base/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 12913164672
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"backbone.blocks.0.filter.D": "model-00001-of-00003.safetensors",
|
| 7 |
+
"backbone.blocks.0.filter.poles": "model-00001-of-00003.safetensors",
|
| 8 |
+
"backbone.blocks.0.filter.residues": "model-00001-of-00003.safetensors",
|
| 9 |
+
"backbone.blocks.0.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 10 |
+
"backbone.blocks.0.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"backbone.blocks.0.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"backbone.blocks.0.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"backbone.blocks.0.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"backbone.blocks.0.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"backbone.blocks.0.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"backbone.blocks.0.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 17 |
+
"backbone.blocks.0.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 18 |
+
"backbone.blocks.0.projections.bias": "model-00001-of-00003.safetensors",
|
| 19 |
+
"backbone.blocks.0.projections.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"backbone.blocks.1.filter.D": "model-00001-of-00003.safetensors",
|
| 21 |
+
"backbone.blocks.1.filter.poles": "model-00001-of-00003.safetensors",
|
| 22 |
+
"backbone.blocks.1.filter.residues": "model-00001-of-00003.safetensors",
|
| 23 |
+
"backbone.blocks.1.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 24 |
+
"backbone.blocks.1.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"backbone.blocks.1.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"backbone.blocks.1.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"backbone.blocks.1.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"backbone.blocks.1.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 29 |
+
"backbone.blocks.1.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"backbone.blocks.1.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 31 |
+
"backbone.blocks.1.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 32 |
+
"backbone.blocks.1.projections.bias": "model-00001-of-00003.safetensors",
|
| 33 |
+
"backbone.blocks.1.projections.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"backbone.blocks.10.filter.D": "model-00001-of-00003.safetensors",
|
| 35 |
+
"backbone.blocks.10.filter.poles": "model-00001-of-00003.safetensors",
|
| 36 |
+
"backbone.blocks.10.filter.residues": "model-00001-of-00003.safetensors",
|
| 37 |
+
"backbone.blocks.10.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 38 |
+
"backbone.blocks.10.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"backbone.blocks.10.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"backbone.blocks.10.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"backbone.blocks.10.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"backbone.blocks.10.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 43 |
+
"backbone.blocks.10.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"backbone.blocks.10.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 45 |
+
"backbone.blocks.10.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 46 |
+
"backbone.blocks.10.projections.bias": "model-00001-of-00003.safetensors",
|
| 47 |
+
"backbone.blocks.10.projections.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"backbone.blocks.11.filter.D": "model-00001-of-00003.safetensors",
|
| 49 |
+
"backbone.blocks.11.filter.poles": "model-00001-of-00003.safetensors",
|
| 50 |
+
"backbone.blocks.11.filter.residues": "model-00001-of-00003.safetensors",
|
| 51 |
+
"backbone.blocks.11.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 52 |
+
"backbone.blocks.11.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"backbone.blocks.11.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"backbone.blocks.11.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"backbone.blocks.11.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"backbone.blocks.11.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 57 |
+
"backbone.blocks.11.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"backbone.blocks.11.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 59 |
+
"backbone.blocks.11.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 60 |
+
"backbone.blocks.11.projections.bias": "model-00001-of-00003.safetensors",
|
| 61 |
+
"backbone.blocks.11.projections.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"backbone.blocks.12.filter.D": "model-00001-of-00003.safetensors",
|
| 63 |
+
"backbone.blocks.12.filter.poles": "model-00001-of-00003.safetensors",
|
| 64 |
+
"backbone.blocks.12.filter.residues": "model-00001-of-00003.safetensors",
|
| 65 |
+
"backbone.blocks.12.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"backbone.blocks.12.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"backbone.blocks.12.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"backbone.blocks.12.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"backbone.blocks.12.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"backbone.blocks.12.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 71 |
+
"backbone.blocks.12.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"backbone.blocks.12.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 73 |
+
"backbone.blocks.12.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 74 |
+
"backbone.blocks.12.projections.bias": "model-00001-of-00003.safetensors",
|
| 75 |
+
"backbone.blocks.12.projections.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"backbone.blocks.13.filter.D": "model-00002-of-00003.safetensors",
|
| 77 |
+
"backbone.blocks.13.filter.poles": "model-00002-of-00003.safetensors",
|
| 78 |
+
"backbone.blocks.13.filter.residues": "model-00002-of-00003.safetensors",
|
| 79 |
+
"backbone.blocks.13.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"backbone.blocks.13.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"backbone.blocks.13.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"backbone.blocks.13.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"backbone.blocks.13.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"backbone.blocks.13.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"backbone.blocks.13.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"backbone.blocks.13.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 87 |
+
"backbone.blocks.13.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 88 |
+
"backbone.blocks.13.projections.bias": "model-00002-of-00003.safetensors",
|
| 89 |
+
"backbone.blocks.13.projections.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"backbone.blocks.14.filter.D": "model-00002-of-00003.safetensors",
|
| 91 |
+
"backbone.blocks.14.filter.poles": "model-00002-of-00003.safetensors",
|
| 92 |
+
"backbone.blocks.14.filter.residues": "model-00002-of-00003.safetensors",
|
| 93 |
+
"backbone.blocks.14.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 94 |
+
"backbone.blocks.14.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"backbone.blocks.14.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"backbone.blocks.14.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"backbone.blocks.14.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"backbone.blocks.14.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"backbone.blocks.14.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"backbone.blocks.14.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 101 |
+
"backbone.blocks.14.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 102 |
+
"backbone.blocks.14.projections.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"backbone.blocks.14.projections.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"backbone.blocks.15.filter.D": "model-00002-of-00003.safetensors",
|
| 105 |
+
"backbone.blocks.15.filter.poles": "model-00002-of-00003.safetensors",
|
| 106 |
+
"backbone.blocks.15.filter.residues": "model-00002-of-00003.safetensors",
|
| 107 |
+
"backbone.blocks.15.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 108 |
+
"backbone.blocks.15.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"backbone.blocks.15.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"backbone.blocks.15.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"backbone.blocks.15.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"backbone.blocks.15.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 113 |
+
"backbone.blocks.15.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"backbone.blocks.15.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 115 |
+
"backbone.blocks.15.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 116 |
+
"backbone.blocks.15.projections.bias": "model-00002-of-00003.safetensors",
|
| 117 |
+
"backbone.blocks.15.projections.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"backbone.blocks.16.inner_mha_cls.Wqkv.bias": "model-00002-of-00003.safetensors",
|
| 119 |
+
"backbone.blocks.16.inner_mha_cls.Wqkv.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"backbone.blocks.16.inner_mha_cls.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 121 |
+
"backbone.blocks.16.inner_mha_cls.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"backbone.blocks.16.inner_mha_cls.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
| 123 |
+
"backbone.blocks.16.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"backbone.blocks.16.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"backbone.blocks.16.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"backbone.blocks.16.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 127 |
+
"backbone.blocks.16.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 128 |
+
"backbone.blocks.17.filter.D": "model-00002-of-00003.safetensors",
|
| 129 |
+
"backbone.blocks.17.filter.poles": "model-00002-of-00003.safetensors",
|
| 130 |
+
"backbone.blocks.17.filter.residues": "model-00002-of-00003.safetensors",
|
| 131 |
+
"backbone.blocks.17.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 132 |
+
"backbone.blocks.17.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"backbone.blocks.17.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"backbone.blocks.17.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"backbone.blocks.17.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"backbone.blocks.17.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 137 |
+
"backbone.blocks.17.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"backbone.blocks.17.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 139 |
+
"backbone.blocks.17.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 140 |
+
"backbone.blocks.17.projections.bias": "model-00002-of-00003.safetensors",
|
| 141 |
+
"backbone.blocks.17.projections.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"backbone.blocks.18.filter.D": "model-00002-of-00003.safetensors",
|
| 143 |
+
"backbone.blocks.18.filter.poles": "model-00002-of-00003.safetensors",
|
| 144 |
+
"backbone.blocks.18.filter.residues": "model-00002-of-00003.safetensors",
|
| 145 |
+
"backbone.blocks.18.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 146 |
+
"backbone.blocks.18.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"backbone.blocks.18.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"backbone.blocks.18.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"backbone.blocks.18.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"backbone.blocks.18.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 151 |
+
"backbone.blocks.18.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"backbone.blocks.18.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 153 |
+
"backbone.blocks.18.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 154 |
+
"backbone.blocks.18.projections.bias": "model-00002-of-00003.safetensors",
|
| 155 |
+
"backbone.blocks.18.projections.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"backbone.blocks.19.filter.D": "model-00002-of-00003.safetensors",
|
| 157 |
+
"backbone.blocks.19.filter.poles": "model-00002-of-00003.safetensors",
|
| 158 |
+
"backbone.blocks.19.filter.residues": "model-00002-of-00003.safetensors",
|
| 159 |
+
"backbone.blocks.19.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 160 |
+
"backbone.blocks.19.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"backbone.blocks.19.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"backbone.blocks.19.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"backbone.blocks.19.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"backbone.blocks.19.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 165 |
+
"backbone.blocks.19.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"backbone.blocks.19.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 167 |
+
"backbone.blocks.19.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 168 |
+
"backbone.blocks.19.projections.bias": "model-00002-of-00003.safetensors",
|
| 169 |
+
"backbone.blocks.19.projections.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"backbone.blocks.2.filter.D": "model-00001-of-00003.safetensors",
|
| 171 |
+
"backbone.blocks.2.filter.poles": "model-00001-of-00003.safetensors",
|
| 172 |
+
"backbone.blocks.2.filter.residues": "model-00001-of-00003.safetensors",
|
| 173 |
+
"backbone.blocks.2.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 174 |
+
"backbone.blocks.2.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 175 |
+
"backbone.blocks.2.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 176 |
+
"backbone.blocks.2.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 177 |
+
"backbone.blocks.2.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 178 |
+
"backbone.blocks.2.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 179 |
+
"backbone.blocks.2.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 180 |
+
"backbone.blocks.2.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 181 |
+
"backbone.blocks.2.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 182 |
+
"backbone.blocks.2.projections.bias": "model-00001-of-00003.safetensors",
|
| 183 |
+
"backbone.blocks.2.projections.weight": "model-00001-of-00003.safetensors",
|
| 184 |
+
"backbone.blocks.20.filter.D": "model-00002-of-00003.safetensors",
|
| 185 |
+
"backbone.blocks.20.filter.poles": "model-00002-of-00003.safetensors",
|
| 186 |
+
"backbone.blocks.20.filter.residues": "model-00002-of-00003.safetensors",
|
| 187 |
+
"backbone.blocks.20.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"backbone.blocks.20.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"backbone.blocks.20.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"backbone.blocks.20.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"backbone.blocks.20.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"backbone.blocks.20.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 193 |
+
"backbone.blocks.20.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"backbone.blocks.20.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 195 |
+
"backbone.blocks.20.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 196 |
+
"backbone.blocks.20.projections.bias": "model-00002-of-00003.safetensors",
|
| 197 |
+
"backbone.blocks.20.projections.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"backbone.blocks.21.filter.D": "model-00002-of-00003.safetensors",
|
| 199 |
+
"backbone.blocks.21.filter.poles": "model-00002-of-00003.safetensors",
|
| 200 |
+
"backbone.blocks.21.filter.residues": "model-00002-of-00003.safetensors",
|
| 201 |
+
"backbone.blocks.21.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 202 |
+
"backbone.blocks.21.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"backbone.blocks.21.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"backbone.blocks.21.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"backbone.blocks.21.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"backbone.blocks.21.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"backbone.blocks.21.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"backbone.blocks.21.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 209 |
+
"backbone.blocks.21.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 210 |
+
"backbone.blocks.21.projections.bias": "model-00002-of-00003.safetensors",
|
| 211 |
+
"backbone.blocks.21.projections.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"backbone.blocks.22.filter.D": "model-00002-of-00003.safetensors",
|
| 213 |
+
"backbone.blocks.22.filter.poles": "model-00002-of-00003.safetensors",
|
| 214 |
+
"backbone.blocks.22.filter.residues": "model-00002-of-00003.safetensors",
|
| 215 |
+
"backbone.blocks.22.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 216 |
+
"backbone.blocks.22.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"backbone.blocks.22.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"backbone.blocks.22.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 219 |
+
"backbone.blocks.22.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"backbone.blocks.22.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 221 |
+
"backbone.blocks.22.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 222 |
+
"backbone.blocks.22.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 223 |
+
"backbone.blocks.22.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 224 |
+
"backbone.blocks.22.projections.bias": "model-00002-of-00003.safetensors",
|
| 225 |
+
"backbone.blocks.22.projections.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"backbone.blocks.23.filter.D": "model-00002-of-00003.safetensors",
|
| 227 |
+
"backbone.blocks.23.filter.poles": "model-00002-of-00003.safetensors",
|
| 228 |
+
"backbone.blocks.23.filter.residues": "model-00002-of-00003.safetensors",
|
| 229 |
+
"backbone.blocks.23.filter.short_filter_bias": "model-00002-of-00003.safetensors",
|
| 230 |
+
"backbone.blocks.23.filter.short_filter_weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"backbone.blocks.23.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"backbone.blocks.23.mlp.l2.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"backbone.blocks.23.mlp.l3.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"backbone.blocks.23.out_filter_dense.bias": "model-00002-of-00003.safetensors",
|
| 235 |
+
"backbone.blocks.23.out_filter_dense.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"backbone.blocks.23.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 237 |
+
"backbone.blocks.23.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 238 |
+
"backbone.blocks.23.projections.bias": "model-00002-of-00003.safetensors",
|
| 239 |
+
"backbone.blocks.23.projections.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"backbone.blocks.24.inner_mha_cls.Wqkv.bias": "model-00002-of-00003.safetensors",
|
| 241 |
+
"backbone.blocks.24.inner_mha_cls.Wqkv.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"backbone.blocks.24.inner_mha_cls.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"backbone.blocks.24.inner_mha_cls.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"backbone.blocks.24.inner_mha_cls.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
| 245 |
+
"backbone.blocks.24.mlp.l1.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"backbone.blocks.24.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 247 |
+
"backbone.blocks.24.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"backbone.blocks.24.post_norm.scale": "model-00002-of-00003.safetensors",
|
| 249 |
+
"backbone.blocks.24.pre_norm.scale": "model-00002-of-00003.safetensors",
|
| 250 |
+
"backbone.blocks.25.filter.D": "model-00003-of-00003.safetensors",
|
| 251 |
+
"backbone.blocks.25.filter.poles": "model-00003-of-00003.safetensors",
|
| 252 |
+
"backbone.blocks.25.filter.residues": "model-00003-of-00003.safetensors",
|
| 253 |
+
"backbone.blocks.25.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 254 |
+
"backbone.blocks.25.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 255 |
+
"backbone.blocks.25.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"backbone.blocks.25.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 257 |
+
"backbone.blocks.25.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"backbone.blocks.25.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"backbone.blocks.25.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"backbone.blocks.25.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 261 |
+
"backbone.blocks.25.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 262 |
+
"backbone.blocks.25.projections.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"backbone.blocks.25.projections.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"backbone.blocks.26.filter.D": "model-00003-of-00003.safetensors",
|
| 265 |
+
"backbone.blocks.26.filter.poles": "model-00003-of-00003.safetensors",
|
| 266 |
+
"backbone.blocks.26.filter.residues": "model-00003-of-00003.safetensors",
|
| 267 |
+
"backbone.blocks.26.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 268 |
+
"backbone.blocks.26.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 269 |
+
"backbone.blocks.26.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"backbone.blocks.26.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 271 |
+
"backbone.blocks.26.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"backbone.blocks.26.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"backbone.blocks.26.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"backbone.blocks.26.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 275 |
+
"backbone.blocks.26.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 276 |
+
"backbone.blocks.26.projections.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"backbone.blocks.26.projections.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"backbone.blocks.27.filter.D": "model-00003-of-00003.safetensors",
|
| 279 |
+
"backbone.blocks.27.filter.poles": "model-00003-of-00003.safetensors",
|
| 280 |
+
"backbone.blocks.27.filter.residues": "model-00003-of-00003.safetensors",
|
| 281 |
+
"backbone.blocks.27.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"backbone.blocks.27.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"backbone.blocks.27.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"backbone.blocks.27.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"backbone.blocks.27.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"backbone.blocks.27.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"backbone.blocks.27.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"backbone.blocks.27.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 289 |
+
"backbone.blocks.27.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 290 |
+
"backbone.blocks.27.projections.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"backbone.blocks.27.projections.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"backbone.blocks.28.filter.D": "model-00003-of-00003.safetensors",
|
| 293 |
+
"backbone.blocks.28.filter.poles": "model-00003-of-00003.safetensors",
|
| 294 |
+
"backbone.blocks.28.filter.residues": "model-00003-of-00003.safetensors",
|
| 295 |
+
"backbone.blocks.28.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 296 |
+
"backbone.blocks.28.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 297 |
+
"backbone.blocks.28.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"backbone.blocks.28.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"backbone.blocks.28.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"backbone.blocks.28.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"backbone.blocks.28.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"backbone.blocks.28.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 303 |
+
"backbone.blocks.28.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 304 |
+
"backbone.blocks.28.projections.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"backbone.blocks.28.projections.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"backbone.blocks.29.filter.D": "model-00003-of-00003.safetensors",
|
| 307 |
+
"backbone.blocks.29.filter.poles": "model-00003-of-00003.safetensors",
|
| 308 |
+
"backbone.blocks.29.filter.residues": "model-00003-of-00003.safetensors",
|
| 309 |
+
"backbone.blocks.29.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 310 |
+
"backbone.blocks.29.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"backbone.blocks.29.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"backbone.blocks.29.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"backbone.blocks.29.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"backbone.blocks.29.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"backbone.blocks.29.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"backbone.blocks.29.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 317 |
+
"backbone.blocks.29.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 318 |
+
"backbone.blocks.29.projections.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"backbone.blocks.29.projections.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"backbone.blocks.3.filter.D": "model-00001-of-00003.safetensors",
|
| 321 |
+
"backbone.blocks.3.filter.poles": "model-00001-of-00003.safetensors",
|
| 322 |
+
"backbone.blocks.3.filter.residues": "model-00001-of-00003.safetensors",
|
| 323 |
+
"backbone.blocks.3.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 324 |
+
"backbone.blocks.3.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 325 |
+
"backbone.blocks.3.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 326 |
+
"backbone.blocks.3.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 327 |
+
"backbone.blocks.3.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 328 |
+
"backbone.blocks.3.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 329 |
+
"backbone.blocks.3.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 330 |
+
"backbone.blocks.3.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 331 |
+
"backbone.blocks.3.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 332 |
+
"backbone.blocks.3.projections.bias": "model-00001-of-00003.safetensors",
|
| 333 |
+
"backbone.blocks.3.projections.weight": "model-00001-of-00003.safetensors",
|
| 334 |
+
"backbone.blocks.30.filter.D": "model-00003-of-00003.safetensors",
|
| 335 |
+
"backbone.blocks.30.filter.poles": "model-00003-of-00003.safetensors",
|
| 336 |
+
"backbone.blocks.30.filter.residues": "model-00003-of-00003.safetensors",
|
| 337 |
+
"backbone.blocks.30.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 338 |
+
"backbone.blocks.30.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 339 |
+
"backbone.blocks.30.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"backbone.blocks.30.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"backbone.blocks.30.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"backbone.blocks.30.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 343 |
+
"backbone.blocks.30.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 344 |
+
"backbone.blocks.30.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 345 |
+
"backbone.blocks.30.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 346 |
+
"backbone.blocks.30.projections.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"backbone.blocks.30.projections.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"backbone.blocks.31.filter.D": "model-00003-of-00003.safetensors",
|
| 349 |
+
"backbone.blocks.31.filter.poles": "model-00003-of-00003.safetensors",
|
| 350 |
+
"backbone.blocks.31.filter.residues": "model-00003-of-00003.safetensors",
|
| 351 |
+
"backbone.blocks.31.filter.short_filter_bias": "model-00003-of-00003.safetensors",
|
| 352 |
+
"backbone.blocks.31.filter.short_filter_weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"backbone.blocks.31.mlp.l1.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"backbone.blocks.31.mlp.l2.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"backbone.blocks.31.mlp.l3.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"backbone.blocks.31.out_filter_dense.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"backbone.blocks.31.out_filter_dense.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"backbone.blocks.31.post_norm.scale": "model-00003-of-00003.safetensors",
|
| 359 |
+
"backbone.blocks.31.pre_norm.scale": "model-00003-of-00003.safetensors",
|
| 360 |
+
"backbone.blocks.31.projections.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"backbone.blocks.31.projections.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"backbone.blocks.4.filter.D": "model-00001-of-00003.safetensors",
|
| 363 |
+
"backbone.blocks.4.filter.poles": "model-00001-of-00003.safetensors",
|
| 364 |
+
"backbone.blocks.4.filter.residues": "model-00001-of-00003.safetensors",
|
| 365 |
+
"backbone.blocks.4.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 366 |
+
"backbone.blocks.4.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 367 |
+
"backbone.blocks.4.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 368 |
+
"backbone.blocks.4.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 369 |
+
"backbone.blocks.4.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"backbone.blocks.4.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 371 |
+
"backbone.blocks.4.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"backbone.blocks.4.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 373 |
+
"backbone.blocks.4.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 374 |
+
"backbone.blocks.4.projections.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"backbone.blocks.4.projections.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"backbone.blocks.5.filter.D": "model-00001-of-00003.safetensors",
|
| 377 |
+
"backbone.blocks.5.filter.poles": "model-00001-of-00003.safetensors",
|
| 378 |
+
"backbone.blocks.5.filter.residues": "model-00001-of-00003.safetensors",
|
| 379 |
+
"backbone.blocks.5.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"backbone.blocks.5.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"backbone.blocks.5.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"backbone.blocks.5.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"backbone.blocks.5.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"backbone.blocks.5.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 385 |
+
"backbone.blocks.5.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"backbone.blocks.5.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 387 |
+
"backbone.blocks.5.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 388 |
+
"backbone.blocks.5.projections.bias": "model-00001-of-00003.safetensors",
|
| 389 |
+
"backbone.blocks.5.projections.weight": "model-00001-of-00003.safetensors",
|
| 390 |
+
"backbone.blocks.6.filter.D": "model-00001-of-00003.safetensors",
|
| 391 |
+
"backbone.blocks.6.filter.poles": "model-00001-of-00003.safetensors",
|
| 392 |
+
"backbone.blocks.6.filter.residues": "model-00001-of-00003.safetensors",
|
| 393 |
+
"backbone.blocks.6.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 394 |
+
"backbone.blocks.6.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"backbone.blocks.6.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"backbone.blocks.6.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"backbone.blocks.6.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"backbone.blocks.6.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"backbone.blocks.6.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"backbone.blocks.6.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 401 |
+
"backbone.blocks.6.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 402 |
+
"backbone.blocks.6.projections.bias": "model-00001-of-00003.safetensors",
|
| 403 |
+
"backbone.blocks.6.projections.weight": "model-00001-of-00003.safetensors",
|
| 404 |
+
"backbone.blocks.7.filter.D": "model-00001-of-00003.safetensors",
|
| 405 |
+
"backbone.blocks.7.filter.poles": "model-00001-of-00003.safetensors",
|
| 406 |
+
"backbone.blocks.7.filter.residues": "model-00001-of-00003.safetensors",
|
| 407 |
+
"backbone.blocks.7.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 408 |
+
"backbone.blocks.7.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"backbone.blocks.7.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"backbone.blocks.7.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 411 |
+
"backbone.blocks.7.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"backbone.blocks.7.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 413 |
+
"backbone.blocks.7.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 414 |
+
"backbone.blocks.7.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 415 |
+
"backbone.blocks.7.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 416 |
+
"backbone.blocks.7.projections.bias": "model-00001-of-00003.safetensors",
|
| 417 |
+
"backbone.blocks.7.projections.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"backbone.blocks.8.inner_mha_cls.Wqkv.bias": "model-00001-of-00003.safetensors",
|
| 419 |
+
"backbone.blocks.8.inner_mha_cls.Wqkv.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"backbone.blocks.8.inner_mha_cls.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 421 |
+
"backbone.blocks.8.inner_mha_cls.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"backbone.blocks.8.inner_mha_cls.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
| 423 |
+
"backbone.blocks.8.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"backbone.blocks.8.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"backbone.blocks.8.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 426 |
+
"backbone.blocks.8.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 427 |
+
"backbone.blocks.8.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 428 |
+
"backbone.blocks.9.filter.D": "model-00001-of-00003.safetensors",
|
| 429 |
+
"backbone.blocks.9.filter.poles": "model-00001-of-00003.safetensors",
|
| 430 |
+
"backbone.blocks.9.filter.residues": "model-00001-of-00003.safetensors",
|
| 431 |
+
"backbone.blocks.9.filter.short_filter_bias": "model-00001-of-00003.safetensors",
|
| 432 |
+
"backbone.blocks.9.filter.short_filter_weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"backbone.blocks.9.mlp.l1.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"backbone.blocks.9.mlp.l2.weight": "model-00001-of-00003.safetensors",
|
| 435 |
+
"backbone.blocks.9.mlp.l3.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"backbone.blocks.9.out_filter_dense.bias": "model-00001-of-00003.safetensors",
|
| 437 |
+
"backbone.blocks.9.out_filter_dense.weight": "model-00001-of-00003.safetensors",
|
| 438 |
+
"backbone.blocks.9.post_norm.scale": "model-00001-of-00003.safetensors",
|
| 439 |
+
"backbone.blocks.9.pre_norm.scale": "model-00001-of-00003.safetensors",
|
| 440 |
+
"backbone.blocks.9.projections.bias": "model-00001-of-00003.safetensors",
|
| 441 |
+
"backbone.blocks.9.projections.weight": "model-00001-of-00003.safetensors",
|
| 442 |
+
"backbone.embedding_layer.weight": "model-00001-of-00003.safetensors",
|
| 443 |
+
"backbone.norm.scale": "model-00001-of-00003.safetensors"
|
| 444 |
+
}
|
| 445 |
+
}
|
evo-1-8k-base/evo-1-8k-base/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
evo-1-8k-base/evo-1-8k-base/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoTokenizer": [
|
| 5 |
+
"tokenizer.ByteTokenizer",
|
| 6 |
+
null
|
| 7 |
+
]
|
| 8 |
+
},
|
| 9 |
+
"byte_level": true,
|
| 10 |
+
"clean_up_tokenization_spaces": true,
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"padding_side": "left",
|
| 13 |
+
"truncation_side": "left"
|
| 14 |
+
}
|
evo-1-8k-base/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 12913164672
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"backbone.blocks.0.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 7 |
+
"backbone.blocks.0.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"backbone.blocks.0.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"backbone.blocks.0.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"backbone.blocks.0.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"backbone.blocks.0.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"backbone.blocks.0.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"backbone.blocks.0.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"backbone.blocks.0.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"backbone.blocks.0.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"backbone.blocks.0.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"backbone.blocks.0.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"backbone.blocks.0.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"backbone.blocks.0.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"backbone.blocks.1.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"backbone.blocks.1.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"backbone.blocks.1.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"backbone.blocks.1.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"backbone.blocks.1.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"backbone.blocks.1.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"backbone.blocks.1.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"backbone.blocks.1.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"backbone.blocks.1.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"backbone.blocks.1.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"backbone.blocks.1.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"backbone.blocks.1.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"backbone.blocks.1.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"backbone.blocks.1.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"backbone.blocks.10.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"backbone.blocks.10.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 36 |
+
"backbone.blocks.10.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"backbone.blocks.10.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"backbone.blocks.10.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 39 |
+
"backbone.blocks.10.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 40 |
+
"backbone.blocks.10.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"backbone.blocks.10.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 42 |
+
"backbone.blocks.10.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 43 |
+
"backbone.blocks.10.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"backbone.blocks.10.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 45 |
+
"backbone.blocks.10.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 46 |
+
"backbone.blocks.10.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 47 |
+
"backbone.blocks.10.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 48 |
+
"backbone.blocks.11.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 49 |
+
"backbone.blocks.11.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 50 |
+
"backbone.blocks.11.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 51 |
+
"backbone.blocks.11.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 52 |
+
"backbone.blocks.11.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 53 |
+
"backbone.blocks.11.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 54 |
+
"backbone.blocks.11.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 55 |
+
"backbone.blocks.11.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 56 |
+
"backbone.blocks.11.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 57 |
+
"backbone.blocks.11.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 58 |
+
"backbone.blocks.11.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 59 |
+
"backbone.blocks.11.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 60 |
+
"backbone.blocks.11.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 61 |
+
"backbone.blocks.11.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 62 |
+
"backbone.blocks.12.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 63 |
+
"backbone.blocks.12.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 64 |
+
"backbone.blocks.12.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 65 |
+
"backbone.blocks.12.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 66 |
+
"backbone.blocks.12.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 67 |
+
"backbone.blocks.12.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 68 |
+
"backbone.blocks.12.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 69 |
+
"backbone.blocks.12.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 70 |
+
"backbone.blocks.12.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 71 |
+
"backbone.blocks.12.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 72 |
+
"backbone.blocks.12.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 73 |
+
"backbone.blocks.12.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 74 |
+
"backbone.blocks.12.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 75 |
+
"backbone.blocks.12.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 76 |
+
"backbone.blocks.13.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 77 |
+
"backbone.blocks.13.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"backbone.blocks.13.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"backbone.blocks.13.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"backbone.blocks.13.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"backbone.blocks.13.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"backbone.blocks.13.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"backbone.blocks.13.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"backbone.blocks.13.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"backbone.blocks.13.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"backbone.blocks.13.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"backbone.blocks.13.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"backbone.blocks.13.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"backbone.blocks.13.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"backbone.blocks.14.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"backbone.blocks.14.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"backbone.blocks.14.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"backbone.blocks.14.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"backbone.blocks.14.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"backbone.blocks.14.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"backbone.blocks.14.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"backbone.blocks.14.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"backbone.blocks.14.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"backbone.blocks.14.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"backbone.blocks.14.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"backbone.blocks.14.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"backbone.blocks.14.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"backbone.blocks.14.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"backbone.blocks.15.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"backbone.blocks.15.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"backbone.blocks.15.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"backbone.blocks.15.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"backbone.blocks.15.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"backbone.blocks.15.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"backbone.blocks.15.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"backbone.blocks.15.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"backbone.blocks.15.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"backbone.blocks.15.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"backbone.blocks.15.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"backbone.blocks.15.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"backbone.blocks.15.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 117 |
+
"backbone.blocks.15.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 118 |
+
"backbone.blocks.16.inner_mha_cls.Wqkv.bias": "pytorch_model-00002-of-00003.bin",
|
| 119 |
+
"backbone.blocks.16.inner_mha_cls.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
| 120 |
+
"backbone.blocks.16.inner_mha_cls.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 121 |
+
"backbone.blocks.16.inner_mha_cls.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 122 |
+
"backbone.blocks.16.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 123 |
+
"backbone.blocks.16.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 124 |
+
"backbone.blocks.16.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 125 |
+
"backbone.blocks.16.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"backbone.blocks.16.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"backbone.blocks.16.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"backbone.blocks.17.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 129 |
+
"backbone.blocks.17.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 130 |
+
"backbone.blocks.17.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 131 |
+
"backbone.blocks.17.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 132 |
+
"backbone.blocks.17.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 133 |
+
"backbone.blocks.17.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 134 |
+
"backbone.blocks.17.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 135 |
+
"backbone.blocks.17.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 136 |
+
"backbone.blocks.17.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 137 |
+
"backbone.blocks.17.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 138 |
+
"backbone.blocks.17.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"backbone.blocks.17.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"backbone.blocks.17.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"backbone.blocks.17.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"backbone.blocks.18.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"backbone.blocks.18.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"backbone.blocks.18.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"backbone.blocks.18.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"backbone.blocks.18.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"backbone.blocks.18.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"backbone.blocks.18.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"backbone.blocks.18.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"backbone.blocks.18.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"backbone.blocks.18.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"backbone.blocks.18.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 153 |
+
"backbone.blocks.18.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 154 |
+
"backbone.blocks.18.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"backbone.blocks.18.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"backbone.blocks.19.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 157 |
+
"backbone.blocks.19.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"backbone.blocks.19.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"backbone.blocks.19.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"backbone.blocks.19.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"backbone.blocks.19.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 162 |
+
"backbone.blocks.19.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 163 |
+
"backbone.blocks.19.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"backbone.blocks.19.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"backbone.blocks.19.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"backbone.blocks.19.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"backbone.blocks.19.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"backbone.blocks.19.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 169 |
+
"backbone.blocks.19.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"backbone.blocks.2.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 171 |
+
"backbone.blocks.2.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 172 |
+
"backbone.blocks.2.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 173 |
+
"backbone.blocks.2.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 174 |
+
"backbone.blocks.2.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 175 |
+
"backbone.blocks.2.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 176 |
+
"backbone.blocks.2.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 177 |
+
"backbone.blocks.2.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 178 |
+
"backbone.blocks.2.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 179 |
+
"backbone.blocks.2.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 180 |
+
"backbone.blocks.2.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 181 |
+
"backbone.blocks.2.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 182 |
+
"backbone.blocks.2.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 183 |
+
"backbone.blocks.2.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 184 |
+
"backbone.blocks.20.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 185 |
+
"backbone.blocks.20.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 186 |
+
"backbone.blocks.20.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 187 |
+
"backbone.blocks.20.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 188 |
+
"backbone.blocks.20.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 189 |
+
"backbone.blocks.20.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 190 |
+
"backbone.blocks.20.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 191 |
+
"backbone.blocks.20.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 192 |
+
"backbone.blocks.20.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 193 |
+
"backbone.blocks.20.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 194 |
+
"backbone.blocks.20.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 195 |
+
"backbone.blocks.20.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 196 |
+
"backbone.blocks.20.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 197 |
+
"backbone.blocks.20.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 198 |
+
"backbone.blocks.21.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 199 |
+
"backbone.blocks.21.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 200 |
+
"backbone.blocks.21.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 201 |
+
"backbone.blocks.21.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 202 |
+
"backbone.blocks.21.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 203 |
+
"backbone.blocks.21.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 204 |
+
"backbone.blocks.21.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 205 |
+
"backbone.blocks.21.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 206 |
+
"backbone.blocks.21.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 207 |
+
"backbone.blocks.21.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 208 |
+
"backbone.blocks.21.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 209 |
+
"backbone.blocks.21.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 210 |
+
"backbone.blocks.21.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 211 |
+
"backbone.blocks.21.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 212 |
+
"backbone.blocks.22.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 213 |
+
"backbone.blocks.22.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 214 |
+
"backbone.blocks.22.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 215 |
+
"backbone.blocks.22.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 216 |
+
"backbone.blocks.22.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 217 |
+
"backbone.blocks.22.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 218 |
+
"backbone.blocks.22.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 219 |
+
"backbone.blocks.22.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 220 |
+
"backbone.blocks.22.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 221 |
+
"backbone.blocks.22.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 222 |
+
"backbone.blocks.22.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 223 |
+
"backbone.blocks.22.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 224 |
+
"backbone.blocks.22.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 225 |
+
"backbone.blocks.22.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 226 |
+
"backbone.blocks.23.filter.D": "pytorch_model-00002-of-00003.bin",
|
| 227 |
+
"backbone.blocks.23.filter.poles": "pytorch_model-00002-of-00003.bin",
|
| 228 |
+
"backbone.blocks.23.filter.residues": "pytorch_model-00002-of-00003.bin",
|
| 229 |
+
"backbone.blocks.23.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
|
| 230 |
+
"backbone.blocks.23.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
|
| 231 |
+
"backbone.blocks.23.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 232 |
+
"backbone.blocks.23.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
|
| 233 |
+
"backbone.blocks.23.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
|
| 234 |
+
"backbone.blocks.23.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
|
| 235 |
+
"backbone.blocks.23.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
|
| 236 |
+
"backbone.blocks.23.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 237 |
+
"backbone.blocks.23.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 238 |
+
"backbone.blocks.23.projections.bias": "pytorch_model-00002-of-00003.bin",
|
| 239 |
+
"backbone.blocks.23.projections.weight": "pytorch_model-00002-of-00003.bin",
|
| 240 |
+
"backbone.blocks.24.inner_mha_cls.Wqkv.bias": "pytorch_model-00002-of-00003.bin",
|
| 241 |
+
"backbone.blocks.24.inner_mha_cls.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
| 242 |
+
"backbone.blocks.24.inner_mha_cls.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 243 |
+
"backbone.blocks.24.inner_mha_cls.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 244 |
+
"backbone.blocks.24.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 245 |
+
"backbone.blocks.24.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
|
| 246 |
+
"backbone.blocks.24.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 247 |
+
"backbone.blocks.24.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 248 |
+
"backbone.blocks.24.post_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 249 |
+
"backbone.blocks.24.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
|
| 250 |
+
"backbone.blocks.25.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 251 |
+
"backbone.blocks.25.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 252 |
+
"backbone.blocks.25.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"backbone.blocks.25.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 254 |
+
"backbone.blocks.25.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 255 |
+
"backbone.blocks.25.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 256 |
+
"backbone.blocks.25.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 257 |
+
"backbone.blocks.25.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 258 |
+
"backbone.blocks.25.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"backbone.blocks.25.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"backbone.blocks.25.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"backbone.blocks.25.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"backbone.blocks.25.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"backbone.blocks.25.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"backbone.blocks.26.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"backbone.blocks.26.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"backbone.blocks.26.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"backbone.blocks.26.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"backbone.blocks.26.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 269 |
+
"backbone.blocks.26.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 270 |
+
"backbone.blocks.26.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 271 |
+
"backbone.blocks.26.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 272 |
+
"backbone.blocks.26.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 273 |
+
"backbone.blocks.26.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 274 |
+
"backbone.blocks.26.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 275 |
+
"backbone.blocks.26.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 276 |
+
"backbone.blocks.26.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 277 |
+
"backbone.blocks.26.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 278 |
+
"backbone.blocks.27.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 279 |
+
"backbone.blocks.27.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 280 |
+
"backbone.blocks.27.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 281 |
+
"backbone.blocks.27.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 282 |
+
"backbone.blocks.27.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 283 |
+
"backbone.blocks.27.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 284 |
+
"backbone.blocks.27.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 285 |
+
"backbone.blocks.27.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 286 |
+
"backbone.blocks.27.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 287 |
+
"backbone.blocks.27.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 288 |
+
"backbone.blocks.27.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 289 |
+
"backbone.blocks.27.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 290 |
+
"backbone.blocks.27.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 291 |
+
"backbone.blocks.27.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 292 |
+
"backbone.blocks.28.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 293 |
+
"backbone.blocks.28.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 294 |
+
"backbone.blocks.28.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 295 |
+
"backbone.blocks.28.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 296 |
+
"backbone.blocks.28.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 297 |
+
"backbone.blocks.28.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 298 |
+
"backbone.blocks.28.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 299 |
+
"backbone.blocks.28.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 300 |
+
"backbone.blocks.28.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 301 |
+
"backbone.blocks.28.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 302 |
+
"backbone.blocks.28.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 303 |
+
"backbone.blocks.28.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 304 |
+
"backbone.blocks.28.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 305 |
+
"backbone.blocks.28.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 306 |
+
"backbone.blocks.29.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 307 |
+
"backbone.blocks.29.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 308 |
+
"backbone.blocks.29.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 309 |
+
"backbone.blocks.29.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 310 |
+
"backbone.blocks.29.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 311 |
+
"backbone.blocks.29.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 312 |
+
"backbone.blocks.29.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 313 |
+
"backbone.blocks.29.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 314 |
+
"backbone.blocks.29.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 315 |
+
"backbone.blocks.29.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 316 |
+
"backbone.blocks.29.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 317 |
+
"backbone.blocks.29.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 318 |
+
"backbone.blocks.29.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 319 |
+
"backbone.blocks.29.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 320 |
+
"backbone.blocks.3.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 321 |
+
"backbone.blocks.3.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 322 |
+
"backbone.blocks.3.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 323 |
+
"backbone.blocks.3.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 324 |
+
"backbone.blocks.3.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 325 |
+
"backbone.blocks.3.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 326 |
+
"backbone.blocks.3.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 327 |
+
"backbone.blocks.3.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 328 |
+
"backbone.blocks.3.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 329 |
+
"backbone.blocks.3.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 330 |
+
"backbone.blocks.3.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 331 |
+
"backbone.blocks.3.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 332 |
+
"backbone.blocks.3.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 333 |
+
"backbone.blocks.3.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 334 |
+
"backbone.blocks.30.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 335 |
+
"backbone.blocks.30.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 336 |
+
"backbone.blocks.30.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 337 |
+
"backbone.blocks.30.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 338 |
+
"backbone.blocks.30.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 339 |
+
"backbone.blocks.30.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 340 |
+
"backbone.blocks.30.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 341 |
+
"backbone.blocks.30.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 342 |
+
"backbone.blocks.30.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 343 |
+
"backbone.blocks.30.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 344 |
+
"backbone.blocks.30.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 345 |
+
"backbone.blocks.30.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 346 |
+
"backbone.blocks.30.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 347 |
+
"backbone.blocks.30.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 348 |
+
"backbone.blocks.31.filter.D": "pytorch_model-00003-of-00003.bin",
|
| 349 |
+
"backbone.blocks.31.filter.poles": "pytorch_model-00003-of-00003.bin",
|
| 350 |
+
"backbone.blocks.31.filter.residues": "pytorch_model-00003-of-00003.bin",
|
| 351 |
+
"backbone.blocks.31.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
|
| 352 |
+
"backbone.blocks.31.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
|
| 353 |
+
"backbone.blocks.31.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
|
| 354 |
+
"backbone.blocks.31.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
|
| 355 |
+
"backbone.blocks.31.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
|
| 356 |
+
"backbone.blocks.31.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
|
| 357 |
+
"backbone.blocks.31.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
|
| 358 |
+
"backbone.blocks.31.post_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 359 |
+
"backbone.blocks.31.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
|
| 360 |
+
"backbone.blocks.31.projections.bias": "pytorch_model-00003-of-00003.bin",
|
| 361 |
+
"backbone.blocks.31.projections.weight": "pytorch_model-00003-of-00003.bin",
|
| 362 |
+
"backbone.blocks.4.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 363 |
+
"backbone.blocks.4.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 364 |
+
"backbone.blocks.4.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 365 |
+
"backbone.blocks.4.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 366 |
+
"backbone.blocks.4.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 367 |
+
"backbone.blocks.4.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 368 |
+
"backbone.blocks.4.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 369 |
+
"backbone.blocks.4.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 370 |
+
"backbone.blocks.4.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 371 |
+
"backbone.blocks.4.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 372 |
+
"backbone.blocks.4.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 373 |
+
"backbone.blocks.4.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 374 |
+
"backbone.blocks.4.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 375 |
+
"backbone.blocks.4.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 376 |
+
"backbone.blocks.5.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 377 |
+
"backbone.blocks.5.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 378 |
+
"backbone.blocks.5.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 379 |
+
"backbone.blocks.5.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 380 |
+
"backbone.blocks.5.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 381 |
+
"backbone.blocks.5.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 382 |
+
"backbone.blocks.5.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 383 |
+
"backbone.blocks.5.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 384 |
+
"backbone.blocks.5.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 385 |
+
"backbone.blocks.5.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 386 |
+
"backbone.blocks.5.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 387 |
+
"backbone.blocks.5.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 388 |
+
"backbone.blocks.5.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 389 |
+
"backbone.blocks.5.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 390 |
+
"backbone.blocks.6.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 391 |
+
"backbone.blocks.6.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 392 |
+
"backbone.blocks.6.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 393 |
+
"backbone.blocks.6.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 394 |
+
"backbone.blocks.6.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 395 |
+
"backbone.blocks.6.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 396 |
+
"backbone.blocks.6.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 397 |
+
"backbone.blocks.6.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 398 |
+
"backbone.blocks.6.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 399 |
+
"backbone.blocks.6.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 400 |
+
"backbone.blocks.6.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 401 |
+
"backbone.blocks.6.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 402 |
+
"backbone.blocks.6.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 403 |
+
"backbone.blocks.6.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 404 |
+
"backbone.blocks.7.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 405 |
+
"backbone.blocks.7.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 406 |
+
"backbone.blocks.7.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 407 |
+
"backbone.blocks.7.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 408 |
+
"backbone.blocks.7.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 409 |
+
"backbone.blocks.7.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 410 |
+
"backbone.blocks.7.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 411 |
+
"backbone.blocks.7.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 412 |
+
"backbone.blocks.7.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 413 |
+
"backbone.blocks.7.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 414 |
+
"backbone.blocks.7.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 415 |
+
"backbone.blocks.7.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 416 |
+
"backbone.blocks.7.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 417 |
+
"backbone.blocks.7.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 418 |
+
"backbone.blocks.8.inner_mha_cls.Wqkv.bias": "pytorch_model-00001-of-00003.bin",
|
| 419 |
+
"backbone.blocks.8.inner_mha_cls.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
| 420 |
+
"backbone.blocks.8.inner_mha_cls.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 421 |
+
"backbone.blocks.8.inner_mha_cls.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 422 |
+
"backbone.blocks.8.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 423 |
+
"backbone.blocks.8.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 424 |
+
"backbone.blocks.8.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 425 |
+
"backbone.blocks.8.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 426 |
+
"backbone.blocks.8.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 427 |
+
"backbone.blocks.8.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 428 |
+
"backbone.blocks.9.filter.D": "pytorch_model-00001-of-00003.bin",
|
| 429 |
+
"backbone.blocks.9.filter.poles": "pytorch_model-00001-of-00003.bin",
|
| 430 |
+
"backbone.blocks.9.filter.residues": "pytorch_model-00001-of-00003.bin",
|
| 431 |
+
"backbone.blocks.9.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
|
| 432 |
+
"backbone.blocks.9.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
|
| 433 |
+
"backbone.blocks.9.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
|
| 434 |
+
"backbone.blocks.9.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
|
| 435 |
+
"backbone.blocks.9.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
|
| 436 |
+
"backbone.blocks.9.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
|
| 437 |
+
"backbone.blocks.9.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
|
| 438 |
+
"backbone.blocks.9.post_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 439 |
+
"backbone.blocks.9.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 440 |
+
"backbone.blocks.9.projections.bias": "pytorch_model-00001-of-00003.bin",
|
| 441 |
+
"backbone.blocks.9.projections.weight": "pytorch_model-00001-of-00003.bin",
|
| 442 |
+
"backbone.embedding_layer.weight": "pytorch_model-00001-of-00003.bin",
|
| 443 |
+
"backbone.norm.scale": "pytorch_model-00001-of-00003.bin",
|
| 444 |
+
"backbone.unembed.weight": "pytorch_model-00001-of-00003.bin"
|
| 445 |
+
}
|
| 446 |
+
}
|
evo-1-8k-base/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
evo-1-8k-base/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoTokenizer": [
|
| 5 |
+
"tokenizer.ByteTokenizer",
|
| 6 |
+
null
|
| 7 |
+
]
|
| 8 |
+
},
|
| 9 |
+
"byte_level": true,
|
| 10 |
+
"clean_up_tokenization_spaces": true,
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"padding_side": "left",
|
| 13 |
+
"truncation_side": "left"
|
| 14 |
+
}
|