beomi/KoAlpaca-Polyglot-12.8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: beomi/KoAlpaca-Polyglot-12.8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-27 20:58:00 +08:00
commit 589afcee04
41 changed files with 60741 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.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
*.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

53
README.md Normal file
View File

@@ -0,0 +1,53 @@
---
language:
- ko
license: apache-2.0
tags:
- generated_from_trainer
- polyglot-ko
- gpt-neox
- KoAlpaca
datasets:
- KoAlpaca-v1.1b
pipeline_tag: text-generation
base_model: EleutherAI/polyglot-ko-12.8b
model-index:
- name: KoAlpaca-Polyglot-12.8B
results: []
---
Update @ 2023.06.01
- Add Safetensor sharded model weight (max shard = 1GB)
# KoAlpaca-Polyglot-12.8B (v1.1b)
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- seed: 42
- distributed_type: multi-GPU (A100 80G)
- num_devices: 4
- gradient_accumulation_steps: 64
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.99,
"train_loss": 0.7372576573065349,
"train_runtime": 28706.0932,
"train_samples": 57593,
"train_samples_per_second": 4.013,
"train_steps_per_second": 0.016
}

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "KoAlpaca-Polyglot-12.8B/",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"classifier_dropout": 0.1,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 20480,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_steps": "global_step301000",
"rotary_emb_base": 10000,
"rotary_pct": 0.5,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 30003
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 0,
"transformers_version": "4.29.2"
}

3
model-00001-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b75ecfe0e19b4ab2164f9f3a308cb73b898046d054192ce78988b2aa62beeb5
size 944941900

3
model-00002-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:332ee09505e2c06b0bca64b233f5433a734c0f470c57fbcd13c3c2753695bde5
size 843231522

3
model-00003-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c1101f6cab5216da681b1a9db699d38ce131878509032a51a77f39f3b3715bc
size 843231290

3
model-00004-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0aafd4df07902f106360058517e97d8240a68a339dc97d7f07782a2a3b789a5
size 1004754108

3
model-00005-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0408b5182d1df8ac38781aea163543ce05f9c77ec87d5851d482c0f5e4870459
size 895670546

3
model-00006-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46b15b3bce2d14663701d103304b5b7ec63bc6c6abec64fee9d0da815ceab3d0
size 1004754108

3
model-00007-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc949de9e4c287efe88fd57b5e4004849ca9d6d80cd9a62faf7f0e737ecb4429
size 895670546

3
model-00008-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1cc5d9d16023c38c2b7ec406ece570c2017a046d32aa21b925f7ab84fff1940d
size 1004754132

3
model-00009-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f88e3a8002ccb516813bc18544a9176bc43034cdd36b62eca0c87c150fcb6cc0
size 895670570

3
model-00010-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e36f14878b5e4a92d9c3992b5c512510dea390d4d3384701f5e6b0f3bb71c510
size 1004754140

3
model-00011-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d48570e079c1e4226f82cb8bec2b1603384e87ba4cb06546d893f2ad511f3979
size 895670570

3
model-00012-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a4f947a735e11085efccfb268d13ee68318d70a080bc516b6adb57b7f2172b1
size 1004754140

3
model-00013-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9ce245267642dd5fb7a0db25d4d821f219d7e39f58277a17aa5ff7006e3c8d3
size 895670570

3
model-00014-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:87038da0bfe850d4cffb4261f8d93cfb60d2db95cca7d23e9e04179c30c86849
size 1004754140

3
model-00015-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a1cf0c02af3b7ed0d0e42b11393bebed956b0e1fbbf7ec09756dbf335afee65
size 895670570

3
model-00016-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f967f43563ee9955d4f00ceb40c583f5bdd6c774dd6f151b731d2e045a6112a1
size 1004754140

3
model-00017-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10bf7d09e21941b1762f34e91b9133eefc214e5704949d63c361cf39bb115451
size 895670570

3
model-00018-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1dd8909a2ef1496b10d236b141e5e07d23a7eecd275f146c87e00fffd1e5ba4e
size 1004754140

3
model-00019-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4fbd5fc94493b8498753caad013bdc62ba59ce759ba1578a5074e647c5a1eb4b
size 895670570

3
model-00020-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:841059522736367e3bfe116a48eff91c5c681f5828a81cca58b34cc1c5f5821d
size 1004754140

3
model-00021-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8468a36840122a25e1b5434957172930b413e49a8557b480983f12740ddc2892
size 895670570

3
model-00022-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:59f1cbb454e3d7fd1776c2194dbdf1cf0c8313c367c5fc704e6a993e333aaa67
size 1004754140

3
model-00023-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe0bf2683ef03d72c4d73d025b5dbd71f6f19d300cf6eb80402adf8177914f1c
size 895670570

3
model-00024-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de48e932519e6ce632b4de3a2f180afc28cdac2435f03ef2ecda580f6fb1a793
size 1004754140

3
model-00025-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6451353f2b930e79d31dec4b4577bf04f7be2ed017c91a1bf7a87c052b60abed
size 895670570

3
model-00026-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac8c7ce10eac1ece1f46cdaaf81cbc076fdaa824356acde66ea455871070e1ae
size 1004754140

3
model-00027-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a783fc4d77f01c93e0852327c7ffde3ab1595fdb2edfa505fa9ea39837f98617
size 895670570

3
model-00028-of-00028.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ac7a4800077cdd394c533512de1ac9849c79d4bee08202bee1bff860ea93c78
size 516977208

611
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,611 @@
{
"metadata": {
"total_size": 25806607440.0
},
"weight_map": {
"embed_out.weight": "model-00028-of-00028.safetensors",
"gpt_neox.embed_in.weight": "model-00001-of-00028.safetensors",
"gpt_neox.final_layer_norm.bias": "model-00028-of-00028.safetensors",
"gpt_neox.final_layer_norm.weight": "model-00028-of-00028.safetensors",
"gpt_neox.layers.0.attention.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.attention.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
"gpt_neox.layers.10.attention.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.dense.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.dense.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.masked_bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.input_layernorm.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.attention.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.attention.dense.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.attention.dense.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.attention.masked_bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.input_layernorm.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.input_layernorm.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.12.attention.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.dense.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.dense.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.masked_bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.input_layernorm.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.input_layernorm.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00009-of-00028.safetensors",
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
"gpt_neox.layers.13.attention.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.dense.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.dense.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.masked_bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.input_layernorm.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.attention.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.attention.dense.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.attention.dense.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.attention.masked_bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.input_layernorm.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.input_layernorm.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
"gpt_neox.layers.15.attention.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.dense.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.dense.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.masked_bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.input_layernorm.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.input_layernorm.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00011-of-00028.safetensors",
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
"gpt_neox.layers.16.attention.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.dense.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.dense.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.masked_bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.input_layernorm.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.attention.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.attention.dense.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.attention.dense.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.attention.masked_bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.input_layernorm.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.input_layernorm.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
"gpt_neox.layers.18.attention.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.dense.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.dense.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.masked_bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.query_key_value.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.query_key_value.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.input_layernorm.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.input_layernorm.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-00013-of-00028.safetensors",
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
"gpt_neox.layers.19.attention.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.dense.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.dense.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.masked_bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.input_layernorm.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.2.attention.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.masked_bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00028.safetensors",
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
"gpt_neox.layers.20.attention.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.attention.dense.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.attention.dense.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.attention.masked_bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.input_layernorm.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.input_layernorm.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
"gpt_neox.layers.21.attention.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.dense.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.dense.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.masked_bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.query_key_value.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.query_key_value.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.input_layernorm.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.input_layernorm.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-00015-of-00028.safetensors",
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
"gpt_neox.layers.22.attention.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.dense.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.dense.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.masked_bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.input_layernorm.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.attention.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.attention.dense.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.attention.dense.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.attention.masked_bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.input_layernorm.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.input_layernorm.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
"gpt_neox.layers.24.attention.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.dense.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.dense.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.masked_bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.query_key_value.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.query_key_value.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.input_layernorm.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.input_layernorm.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-00017-of-00028.safetensors",
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
"gpt_neox.layers.25.attention.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.dense.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.dense.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.masked_bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.input_layernorm.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.attention.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.attention.dense.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.attention.dense.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.attention.masked_bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.input_layernorm.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
"gpt_neox.layers.27.attention.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.dense.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.dense.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.masked_bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.query_key_value.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.query_key_value.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.input_layernorm.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-00019-of-00028.safetensors",
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
"gpt_neox.layers.28.attention.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.dense.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.dense.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.masked_bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.input_layernorm.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.attention.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.attention.dense.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.attention.dense.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.attention.masked_bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.input_layernorm.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.input_layernorm.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
"gpt_neox.layers.3.attention.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.dense.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.dense.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.masked_bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.input_layernorm.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00003-of-00028.safetensors",
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
"gpt_neox.layers.30.attention.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.dense.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.dense.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.masked_bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.query_key_value.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.query_key_value.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.input_layernorm.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.input_layernorm.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-00021-of-00028.safetensors",
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
"gpt_neox.layers.31.attention.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.dense.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.dense.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.masked_bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.input_layernorm.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.attention.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.attention.dense.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.attention.dense.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.attention.masked_bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.input_layernorm.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.input_layernorm.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.32.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
"gpt_neox.layers.32.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
"gpt_neox.layers.33.attention.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.dense.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.dense.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.masked_bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.query_key_value.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.query_key_value.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.input_layernorm.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.input_layernorm.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.post_attention_layernorm.bias": "model-00023-of-00028.safetensors",
"gpt_neox.layers.33.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
"gpt_neox.layers.34.attention.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.dense.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.dense.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.masked_bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.input_layernorm.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.attention.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.attention.dense.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.attention.dense.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.attention.masked_bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.input_layernorm.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.input_layernorm.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.35.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
"gpt_neox.layers.35.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
"gpt_neox.layers.36.attention.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.dense.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.dense.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.masked_bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.query_key_value.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.query_key_value.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.input_layernorm.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.input_layernorm.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.post_attention_layernorm.bias": "model-00025-of-00028.safetensors",
"gpt_neox.layers.36.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
"gpt_neox.layers.37.attention.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.dense.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.dense.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.masked_bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.input_layernorm.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.attention.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.attention.dense.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.attention.dense.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.attention.masked_bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.input_layernorm.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.input_layernorm.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.38.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
"gpt_neox.layers.38.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
"gpt_neox.layers.39.attention.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.dense.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.dense.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.masked_bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.query_key_value.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.query_key_value.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.input_layernorm.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.input_layernorm.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00028-of-00028.safetensors",
"gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00028-of-00028.safetensors",
"gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.post_attention_layernorm.bias": "model-00027-of-00028.safetensors",
"gpt_neox.layers.39.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
"gpt_neox.layers.4.attention.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.dense.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.dense.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.masked_bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.input_layernorm.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.attention.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.attention.dense.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.attention.dense.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.attention.masked_bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.input_layernorm.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.input_layernorm.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
"gpt_neox.layers.6.attention.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.dense.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.dense.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.masked_bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.input_layernorm.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00005-of-00028.safetensors",
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
"gpt_neox.layers.7.attention.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.dense.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.dense.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.masked_bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.input_layernorm.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.attention.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.attention.dense.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.attention.dense.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.attention.masked_bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.input_layernorm.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.input_layernorm.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
"gpt_neox.layers.9.attention.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.dense.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.dense.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.masked_bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.input_layernorm.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.input_layernorm.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00007-of-00028.safetensors",
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00007-of-00028.safetensors"
}
}

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4b06c217dc641008ad56030c95d59940d9fd021d87a9c1321e6a5bc721bcc6ed
size 25953607721

11
special_tokens_map.json Normal file
View File

@@ -0,0 +1,11 @@
{
"additional_special_tokens": [
"<|endoftext|>",
"<|sep|>",
"<|acc|>",
"<|tel|>",
"<|rrn|>"
],
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}

59855
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

7
tokenizer_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.99,
"train_loss": 0.7372576573065349,
"train_runtime": 28706.0932,
"train_samples": 57593,
"train_samples_per_second": 4.013,
"train_steps_per_second": 0.016
}

31
trainer_state.json Normal file
View File

@@ -0,0 +1,31 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.991249392318911,
"global_step": 448,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0,
"loss": 2.4259,
"step": 1
},
{
"epoch": 1.99,
"step": 448,
"total_flos": 1883191577149440.0,
"train_loss": 0.7372576573065349,
"train_runtime": 28706.0932,
"train_samples_per_second": 4.013,
"train_steps_per_second": 0.016
}
],
"max_steps": 448,
"num_train_epochs": 2,
"total_flos": 1883191577149440.0,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d16517ebe6740e1b5ae9b137c22d1caae3fb8e1663fe042699314cf61bc64831
size 4859