Add the final OpenStax prose and QA checkpoints
Browse files- README.md +34 -0
- openstax_prose/config.json +34 -0
- openstax_prose/generation_config.json +8 -0
- openstax_prose/merges.txt +0 -0
- openstax_prose/model.safetensors +3 -0
- openstax_prose/special_tokens_map.json +30 -0
- openstax_prose/tokenizer.json +0 -0
- openstax_prose/tokenizer_config.json +193 -0
- openstax_prose/vocab.json +0 -0
- openstax_qa/config.json +34 -0
- openstax_qa/generation_config.json +8 -0
- openstax_qa/merges.txt +0 -0
- openstax_qa/model.safetensors +3 -0
- openstax_qa/special_tokens_map.json +30 -0
- openstax_qa/tokenizer.json +0 -0
- openstax_qa/tokenizer_config.json +193 -0
- openstax_qa/vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- question-answering
|
| 7 |
+
- knowledge-retrieval
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Same Content, Different Format: QA-formatting models
|
| 11 |
+
|
| 12 |
+
Checkpoints of the QA-formatting experiment of *Same Content, Different Format: QA Augmentation and Faded Worked
|
| 13 |
+
Examples Under a Fixed Training Budget*. Each subfolder is a GPT-2-geometry decoder (162.5M parameters, 512-token
|
| 14 |
+
context, Dolma2 tokenizer) trained from scratch only on its arm's renderings of 5,886 OpenStax claims, at the final
|
| 15 |
+
continuation checkpoint (891.5 passes).
|
| 16 |
+
|
| 17 |
+
| Subfolder | Arm |
|
| 18 |
+
|---|---|
|
| 19 |
+
| `openstax_prose` | diverse prose rewrites of each claim |
|
| 20 |
+
| `openstax_qa` | diverse question-answer rewrites of each claim |
|
| 21 |
+
|
| 22 |
+
```python
|
| 23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 24 |
+
tok = AutoTokenizer.from_pretrained("nzhao721/qa-formatting-models", subfolder="openstax_qa")
|
| 25 |
+
model = AutoModelForCausalLM.from_pretrained("nzhao721/qa-formatting-models", subfolder="openstax_qa")
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
The paper scores both with the prompt `Question: {question}\n\nAnswer:` and grades the first `Answer:` field. The
|
| 29 |
+
base checkpoints, the normal-fact arm and the synthetic-data preflight checkpoints are not included. The training
|
| 30 |
+
data and question sets are in
|
| 31 |
+
[nzhao721/qa-formatting-data](https://huggingface.co/datasets/nzhao721/qa-formatting-data).
|
| 32 |
+
|
| 33 |
+
These are research checkpoints trained on OpenStax-derived material, released for non-commercial research use under
|
| 34 |
+
CC BY-NC-SA 4.0; they are not educational QA models. Every arm was trained once with one seed.
|
openstax_prose/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/orcd/scratch/orcd/013/ni_lin/p1hypothesis_openstax_stage2_smoke_20260725/data/stage2_educational/results/openstax_stage2_v4_llm_augmented_k4_no_pack_300m_q1_train_20260725/checkpoint",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 100257,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 512,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"pad_token_id": 100277,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.48.3",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 100278
|
| 34 |
+
}
|
openstax_prose/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"pad_token_id": 100277,
|
| 6 |
+
"transformers_version": "4.48.3",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
openstax_prose/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
openstax_prose/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84a78f8379f6d912f01e1206856df00a9c8e7a0a7d8d907120398b34b247261b
|
| 3 |
+
size 649865856
|
openstax_prose/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
openstax_prose/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
openstax_prose/tokenizer_config.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"max_length": null,
|
| 186 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 187 |
+
"pad_to_multiple_of": null,
|
| 188 |
+
"pad_token": "<|pad|>",
|
| 189 |
+
"pad_token_type_id": 0,
|
| 190 |
+
"padding_side": "left",
|
| 191 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 192 |
+
"unk_token": "<|endoftext|>"
|
| 193 |
+
}
|
openstax_prose/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
openstax_qa/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/orcd/scratch/orcd/013/ni_lin/p1hypothesis_openstax_stage2_smoke_20260725/data/stage2_educational/results/openstax_stage2_v4_llm_augmented_k4_no_pack_300m_q3_train_20260725/checkpoint",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 100257,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 512,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"pad_token_id": 100277,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.48.3",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 100278
|
| 34 |
+
}
|
openstax_qa/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"pad_token_id": 100277,
|
| 6 |
+
"transformers_version": "4.48.3",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
openstax_qa/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
openstax_qa/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fad206f3fbe2e460cfd3ee7c143f3b1d4f54d99c293128475079140f500e2d7
|
| 3 |
+
size 649865856
|
openstax_qa/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
openstax_qa/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
openstax_qa/tokenizer_config.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"max_length": null,
|
| 186 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 187 |
+
"pad_to_multiple_of": null,
|
| 188 |
+
"pad_token": "<|pad|>",
|
| 189 |
+
"pad_token_type_id": 0,
|
| 190 |
+
"padding_side": "left",
|
| 191 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 192 |
+
"unk_token": "<|endoftext|>"
|
| 193 |
+
}
|
openstax_qa/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|