初始化项目，由ModelHub XC社区提供模型
Model: Harvard-DCML/boomerang-pythia-3.8B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
59
README.md
Normal file
59
README.md
Normal file
@@ -0,0 +1,59 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- EleutherAI/the_pile_deduplicated
|
||||
---
|
||||
|
||||
## Model Description
|
||||
|
||||
Boomerang distillation is a phenomenon in LLMs where we can distill a teacher model into a student and reincorporate teacher layers to create intermediate-sized models with no additional training. This is the student model distilled from Pythia-6.9B from [our paper](https://arxiv.org/abs/2510.05064).
|
||||
|
||||
## Training Procedure
|
||||
|
||||
This model was initialized from Pythia-6.9B by copying every other layer and the last 2 layers. It was distilled on 2.1B tokens of The Pile deduplicated with cross entropy, KL, and cosine loss to match the activations of Pythia-6.9B. We used the following hyperparameters:
|
||||
|
||||
- Learning rate: 3e-4
|
||||
- Learning rate scheduler: cosine
|
||||
- Warmup ratio: 0.01
|
||||
- Optimizer: AdamW
|
||||
- Adam betas: (0.9, 0.95)
|
||||
- Adam epsilon: 1e-8
|
||||
- Weight decay: 0.1
|
||||
- Max. gradient norm: 1.0
|
||||
- Number of training steps: 500
|
||||
- Max. sequence length: 2048
|
||||
- Effective batch size: 2048
|
||||
- Mixed precision: bf16
|
||||
- KLDiv weight: 0.1
|
||||
- Cosine distance weight per layer: 0.11
|
||||
|
||||
## Use
|
||||
|
||||
To interpolate between this model and Pythia-6.9B, please use the `build_intermediate_model` function from [our github repository](https://github.com/dcml-lab/boomerang-distillation):
|
||||
```python3
|
||||
import torch
|
||||
from patching.patch import build_intermediate_model
|
||||
|
||||
intermediate_model = build_intermediate_model(
|
||||
teacher_name_or_path = "EleutherAI/pythia-6.9b",
|
||||
student_name_or_path = "Harvard-DCML/boomerang-pythia-3.8B",
|
||||
num_layers_to_patch = 2,
|
||||
patch_first_k_layers = False,
|
||||
dtype = torch.bfloat16,
|
||||
)
|
||||
```
|
||||
Notes:
|
||||
1. Changing `num_layers_to_patch` changes the size of the intermediate model by patching different numbers of student layers.
|
||||
2. `patch_first_k_layers` should be set to False for this model for optimal interpolation performance.
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@article{kangaslahti2025boomerang,
|
||||
title={Boomerang Distillation Enables Zero-Shot Model Size Interpolation},
|
||||
author={Kangaslahti, Sara and Nayak, Nihal V and Geuter, Jonathan and Fumero, Marco and Locatello, Francesco and Alvarez-Melis, David},
|
||||
journal={arXiv preprint arXiv:2510.05064},
|
||||
year={2025},
|
||||
url={https://arxiv.org/abs/2510.05064}
|
||||
}
|
||||
```
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 16384,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 17,
|
||||
"partial_rotary_factor": 0.25,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50432
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:601b492fd98b33401bfbada3bb26de44f5ae921af77e94ee4220d5e76b8f9ffd
|
||||
size 4853947896
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c4c0a7659fb407ca39dd25d3301cf84bf7c7b6450120ea5f3d4fcfcdcb500f9
|
||||
size 4833124648
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b57374d2b0caad30a6d8eccb948c01904f2839ca284a98f7b7e2598f7a67a3d1
|
||||
size 4833091672
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2bf336ace233fcf02dbc7646bf64689c89b5755b07d2e3a765c5ed0382834f2
|
||||
size 826278016
|
||||
215
model.safetensors.index.json
Normal file
215
model.safetensors.index.json
Normal file
@@ -0,0 +1,215 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15346417664
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "model-00004-of-00004.safetensors",
|
||||
"gpt_neox.embed_in.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.final_layer_norm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.final_layer_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
1
student_config.json
Normal file
1
student_config.json
Normal file
@@ -0,0 +1 @@
|
||||
{"pruned_teacher_layers": [1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29], "copied_teacher_layers": [0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30, 31]}
|
||||
250591
tokenizer.json
Normal file
250591
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
215
tokenizer_config.json
Normal file
215
tokenizer_config.json
Normal file
@@ -0,0 +1,215 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9b36686a5ea785ee001b198116febd1a2497fba5f042e889830193b0761caad
|
||||
size 5560
|
||||
Reference in New Issue
Block a user