初始化项目，由ModelHub XC社区提供模型
Model: ContextualAI/archangel_ppo_pythia2-8b 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
|
||||
56
README.md
Normal file
56
README.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- stanfordnlp/SHP
|
||||
- Anthropic/hh-rlhf
|
||||
- OpenAssistant/oasst1
|
||||
language:
|
||||
- en
|
||||
metrics:
|
||||
- accuracy
|
||||
tags:
|
||||
- human feedback
|
||||
- rlhf
|
||||
- preferences
|
||||
- alignment
|
||||
- HALO
|
||||
- halos
|
||||
- dpo
|
||||
- rl
|
||||
---
|
||||
|
||||
|
||||
|
||||
This repo contains the model checkpoints for:
|
||||
- model family <b>EleutherAI/pythia-2.8b</b>
|
||||
- optimized with the loss <b>PPO</b>
|
||||
- aligned using the SHP, Anthropic HH and Open Assistant datasets.
|
||||
|
||||
To prompt Archangel models, ensure that the format is consistent with that of TuluV2.
|
||||
For example, a prompt should be formatted as follows, where `<|user|>` corresponds to the human's role and `<|assistant|>` corresponds to the LLM's role.
|
||||
The human should speak first:
|
||||
```
|
||||
<|user|>
|
||||
Hi! I'm looking for a cake recipe.
|
||||
<|assistant|>
|
||||
What kind of cake?
|
||||
<|user|>
|
||||
Chocolate cake.
|
||||
<|assistant|>
|
||||
```
|
||||
Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt.
|
||||
|
||||
|
||||
|
||||
Please refer to our [code repository](https://github.com/ContextualAI/HALOs) or [blog](https://contextual.ai/better-cheaper-faster-llm-alignment-with-kto/) which contains intructions for training your own HALOs and links to our model cards.
|
||||
|
||||
If you find this repo or the technical paper useful in your research, please feel free to cite [our work](https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf):
|
||||
```
|
||||
@techreport{ethayarajh2023halos,
|
||||
author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe},
|
||||
title = {Human-Centered Loss Functions (HALOs)},
|
||||
institution = {Contextual AI},
|
||||
note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf},
|
||||
year = {2023},
|
||||
}
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "EleutherAI/pythia-2.8b",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"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": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"rope_scaling": null,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
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": "4.35.2"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c1a154b5951792136b318e812044456efaab5d63f07cdfaebd2ee16a2be2a590
|
||||
size 4978209248
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc731af57be8f776a64addcaf7e95a12c5527c9d6e5f34d2f04cf1c67566baa5
|
||||
size 572254856
|
||||
395
model.safetensors.index.json
Normal file
395
model.safetensors.index.json
Normal file
@@ -0,0 +1,395 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5550417920
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"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": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100529
tokenizer.json
Normal file
100529
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
212
tokenizer_config.json
Normal file
212
tokenizer_config.json
Normal file
@@ -0,0 +1,212 @@
|
||||
{
|
||||
"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": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user