Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- LICENSE +3 -0
- README.md +71 -3
- added_tokens.json +608 -0
- all_results.json +8 -0
- chat_template.jinja +1 -0
- config.json +32 -0
- generation_config.json +9 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +295 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- train_results.json +8 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Copyright (C) 2024 Xiaomi Corporation.
|
| 2 |
+
|
| 3 |
+
Licensed under the [Gemma](https://ai.google.dev/gemma/terms).
|
README.md
CHANGED
|
@@ -1,3 +1,71 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
license_name: license
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
base_model:
|
| 6 |
+
- ModelSpace/GemmaX2-28-2B-v0.1
|
| 7 |
+
pipeline_tag: translation
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation
|
| 11 |
+
language:
|
| 12 |
+
- de
|
| 13 |
+
- en
|
| 14 |
+
- fr
|
| 15 |
+
- es
|
| 16 |
+
---
|
| 17 |
+
## Model Summary
|
| 18 |
+
|
| 19 |
+
OLaPh is a large language model for phonemization, finetuned from GemmaX2-28-2B-v0.1.
|
| 20 |
+
Its tokenizer was extended with 1,024 phoneme tokens, derived from a BPE tokenizer trained on phoneme sequences generated by the OLaPh framework (to be released).
|
| 21 |
+
|
| 22 |
+
The model was then finetuned for grapheme-to-phoneme conversion on a multilingual dataset (English, German, French, Spanish), created by phonemizing text from HuggingFaceFW/fineweb and HuggingFaceFW/fineweb-2 using the OLaPh framework.
|
| 23 |
+
|
| 24 |
+
- **Finetuned By **: Institute for Information Systems of Hof University
|
| 25 |
+
- **Model type**: Text-To-Text
|
| 26 |
+
- **Language(s)**: English, French, German, Spanish
|
| 27 |
+
- **License**: Gemma (Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms)
|
| 28 |
+
- **Release Date**: September 25, 2025
|
| 29 |
+
|
| 30 |
+
## Usage
|
| 31 |
+
|
| 32 |
+
```python
|
| 33 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 34 |
+
|
| 35 |
+
lang = "English" #German, French, Spanish
|
| 36 |
+
sentence = "But we are not sorry, for the rain is delightful."
|
| 37 |
+
|
| 38 |
+
model_id = "iisys-hof/olaph"
|
| 39 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 40 |
+
model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
|
| 41 |
+
stop_tokens = [tokenizer.eos_token_id, tokenizer.encode(".", add_special_tokens=False)[0]]
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
prompt = f"Translate this from {lang} to Phones:\n{lang}: "
|
| 45 |
+
|
| 46 |
+
inputs = tokenizer(f"{prompt}{sentence}\nPhones:", return_tensors="pt").to("cuda")
|
| 47 |
+
|
| 48 |
+
outputs = model.generate(**inputs, max_new_tokens=256, eos_token_id=stop_tokens)
|
| 49 |
+
phonemized = tokenizer.decode(outputs[0], skip_special_tokens=False)
|
| 50 |
+
phonemized = phonemized.split("\n")[-1].replace("Phones:", "")
|
| 51 |
+
|
| 52 |
+
print(phonemized)
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
#Caveats
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Citation
|
| 61 |
+
```bibtex
|
| 62 |
+
@misc{wirth2025olaphoptimallanguagephonemizer,
|
| 63 |
+
title={OLaPh: Optimal Language Phonemizer},
|
| 64 |
+
author={Johannes Wirth},
|
| 65 |
+
year={2025},
|
| 66 |
+
eprint={2509.20086},
|
| 67 |
+
archivePrefix={arXiv},
|
| 68 |
+
primaryClass={cs.CL},
|
| 69 |
+
url={https://arxiv.org/abs/2509.20086},
|
| 70 |
+
}
|
| 71 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,608 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
" avɛ": 256208,
|
| 3 |
+
" avɛk": 256343,
|
| 4 |
+
" aʁ": 256368,
|
| 5 |
+
" aʊ̯": 256073,
|
| 6 |
+
" aʊ̯f": 256165,
|
| 7 |
+
" aʊ̯s": 256266,
|
| 8 |
+
" aʊ̯x": 256211,
|
| 9 |
+
" baɪ̯": 256333,
|
| 10 |
+
" bjɛ̃": 256478,
|
| 11 |
+
" bə": 256075,
|
| 12 |
+
" bɪk": 256505,
|
| 13 |
+
" bɪs": 256533,
|
| 14 |
+
" bɹ": 256256,
|
| 15 |
+
" dɑ̃": 256175,
|
| 16 |
+
" dɔx": 256523,
|
| 17 |
+
" dɔ̃": 256509,
|
| 18 |
+
" dɛn": 256601,
|
| 19 |
+
" dɛs": 256199,
|
| 20 |
+
" dɪs": 256361,
|
| 21 |
+
" dɹ": 256404,
|
| 22 |
+
" dʊʁç": 256413,
|
| 23 |
+
" dʒ": 256188,
|
| 24 |
+
" etɛ": 256277,
|
| 25 |
+
" fwe": 256511,
|
| 26 |
+
" fɔn": 256146,
|
| 27 |
+
" fɔʁ": 256507,
|
| 28 |
+
" fɛ": 256513,
|
| 29 |
+
" fɛɐ̯": 256091,
|
| 30 |
+
" fɛʁ": 256545,
|
| 31 |
+
" fɹ": 256144,
|
| 32 |
+
" fʁ": 256388,
|
| 33 |
+
" gʁ": 256389,
|
| 34 |
+
" kaʁ": 256458,
|
| 35 |
+
" komo": 256320,
|
| 36 |
+
" kɔ": 256599,
|
| 37 |
+
" kɔm": 256184,
|
| 38 |
+
" kɔ̃": 256135,
|
| 39 |
+
" kə": 256085,
|
| 40 |
+
" kəm": 256311,
|
| 41 |
+
" kən": 256461,
|
| 42 |
+
" kəns": 256600,
|
| 43 |
+
" kɛl": 256517,
|
| 44 |
+
" kɹ": 256315,
|
| 45 |
+
" lœʁ": 256459,
|
| 46 |
+
" lə": 256062,
|
| 47 |
+
" lɥi": 256345,
|
| 48 |
+
" maʁ": 256393,
|
| 49 |
+
" mwa": 256563,
|
| 50 |
+
" mɔ̃": 256330,
|
| 51 |
+
" mɛ": 256227,
|
| 52 |
+
" mɛm": 256550,
|
| 53 |
+
" mɪt": 256147,
|
| 54 |
+
" mɪç": 256407,
|
| 55 |
+
" nɔx": 256324,
|
| 56 |
+
" nɔ̃": 256498,
|
| 57 |
+
" nə": 256224,
|
| 58 |
+
" nɪçt": 256140,
|
| 59 |
+
" otʁ": 256602,
|
| 60 |
+
" paɾ": 256192,
|
| 61 |
+
" paɾa": 256291,
|
| 62 |
+
" paʁ": 256111,
|
| 63 |
+
" peɾ": 256501,
|
| 64 |
+
" peɾo": 256548,
|
| 65 |
+
" poɾ": 256177,
|
| 66 |
+
" puʁ": 256196,
|
| 67 |
+
" pø": 256521,
|
| 68 |
+
" pɔ": 256568,
|
| 69 |
+
" pə": 256514,
|
| 70 |
+
" pɛʁ": 256328,
|
| 71 |
+
" pɹ": 256142,
|
| 72 |
+
" pɹə": 256394,
|
| 73 |
+
" pɾi": 256540,
|
| 74 |
+
" pɾo": 256321,
|
| 75 |
+
" pʁ": 256103,
|
| 76 |
+
" pʁe": 256444,
|
| 77 |
+
" pʁɔ": 256284,
|
| 78 |
+
" seɲ": 256604,
|
| 79 |
+
" stɹ": 256334,
|
| 80 |
+
" syʁ": 256235,
|
| 81 |
+
" sɑ̃": 256289,
|
| 82 |
+
" sɔ̃": 256172,
|
| 83 |
+
" sɛ": 256373,
|
| 84 |
+
" sɛt": 256258,
|
| 85 |
+
" sɛʁ": 256580,
|
| 86 |
+
" sɛ̃": 256453,
|
| 87 |
+
" s̪": 256183,
|
| 88 |
+
" tje": 256520,
|
| 89 |
+
" tɑ̃": 256574,
|
| 90 |
+
" tɹ": 256202,
|
| 91 |
+
" tɾa": 256552,
|
| 92 |
+
" tʁ": 256236,
|
| 93 |
+
" tʁa": 256484,
|
| 94 |
+
" t͡s": 256049,
|
| 95 |
+
" t͡su": 256074,
|
| 96 |
+
" t͡sʊm": 256490,
|
| 97 |
+
" tʃ": 256226,
|
| 98 |
+
" vwa": 256588,
|
| 99 |
+
" vɛn": 256375,
|
| 100 |
+
" vɪ": 256405,
|
| 101 |
+
" vɪɐ̯t": 256406,
|
| 102 |
+
" zaɪ̯n": 256367,
|
| 103 |
+
" zɪnt": 256359,
|
| 104 |
+
" zɪç": 256143,
|
| 105 |
+
" ðə": 256007,
|
| 106 |
+
" œ̃": 256121,
|
| 107 |
+
" ɐ": 256057,
|
| 108 |
+
" ɐb": 256383,
|
| 109 |
+
" ɐd": 256587,
|
| 110 |
+
" ɐl": 256559,
|
| 111 |
+
" ɐɡ": 256472,
|
| 112 |
+
" ɑ̃": 256056,
|
| 113 |
+
" ɑ̃tʁ": 256581,
|
| 114 |
+
" ɔ": 256210,
|
| 115 |
+
" ɔʁ": 256370,
|
| 116 |
+
" ɔ̃": 256254,
|
| 117 |
+
" ənt": 256482,
|
| 118 |
+
" əp": 256538,
|
| 119 |
+
" ɛks": 256259,
|
| 120 |
+
" ɛl": 256193,
|
| 121 |
+
" ɛnt": 256279,
|
| 122 |
+
" ɛs": 256116,
|
| 123 |
+
" ɛst": 256101,
|
| 124 |
+
" ɛtʁ": 256554,
|
| 125 |
+
" ɛɐ̯": 256145,
|
| 126 |
+
" ɛ̃": 256162,
|
| 127 |
+
" ɡ": 256016,
|
| 128 |
+
" ɡl": 256582,
|
| 129 |
+
" ɡə": 256052,
|
| 130 |
+
" ɡɹ": 256214,
|
| 131 |
+
" ɪm": 256158,
|
| 132 |
+
" ɪn": 256053,
|
| 133 |
+
" ɪst": 256138,
|
| 134 |
+
" ɪç": 256120,
|
| 135 |
+
" ɹ": 256039,
|
| 136 |
+
" ɹɪs": 256547,
|
| 137 |
+
" ʁ": 256042,
|
| 138 |
+
" ʁa": 256419,
|
| 139 |
+
" ʁe": 256185,
|
| 140 |
+
" ʁi": 256596,
|
| 141 |
+
" ʁə": 256218,
|
| 142 |
+
" ʃ": 256031,
|
| 143 |
+
" ʃo": 256440,
|
| 144 |
+
" ʃta": 256510,
|
| 145 |
+
" ʊm": 256310,
|
| 146 |
+
" ʊn": 256414,
|
| 147 |
+
" ʊns": 256593,
|
| 148 |
+
" ʊnt": 256035,
|
| 149 |
+
" ʌn": 256519,
|
| 150 |
+
" ʒ": 256079,
|
| 151 |
+
" ʒə": 256215,
|
| 152 |
+
" ʝ": 256391,
|
| 153 |
+
" ʼ": 256428,
|
| 154 |
+
" ˈ": 256000,
|
| 155 |
+
" ˌ": 256064,
|
| 156 |
+
"alə": 256603,
|
| 157 |
+
"ant͡s": 256409,
|
| 158 |
+
"asjɔ̃": 256247,
|
| 159 |
+
"að": 256067,
|
| 160 |
+
"aða": 256305,
|
| 161 |
+
"aðo": 256213,
|
| 162 |
+
"aðos": 256549,
|
| 163 |
+
"aɪ̯": 256004,
|
| 164 |
+
"aɪ̯l": 256357,
|
| 165 |
+
"aɪ̯n": 256018,
|
| 166 |
+
"aɪ̯nɐ": 256249,
|
| 167 |
+
"aɪ̯nə": 256114,
|
| 168 |
+
"aɪ̯nəm": 256293,
|
| 169 |
+
"aɪ̯nən": 256230,
|
| 170 |
+
"aɪ̯nəs": 256558,
|
| 171 |
+
"aɪ̯t": 256137,
|
| 172 |
+
"aɾ": 256043,
|
| 173 |
+
"aʁ": 256026,
|
| 174 |
+
"aʊ̯": 256083,
|
| 175 |
+
"aʊ̯f": 256312,
|
| 176 |
+
"aʊ̯s": 256245,
|
| 177 |
+
"a": 256047,
|
| 178 |
+
"aɪ": 256009,
|
| 179 |
+
"aɪd": 256233,
|
| 180 |
+
"aɪf": 256522,
|
| 181 |
+
"aɪk": 256402,
|
| 182 |
+
"aɪl": 256355,
|
| 183 |
+
"aɪm": 256319,
|
| 184 |
+
"aɪn": 256322,
|
| 185 |
+
"aɪnd": 256358,
|
| 186 |
+
"aɪt": 256168,
|
| 187 |
+
"aɪv": 256515,
|
| 188 |
+
"aɪz": 256381,
|
| 189 |
+
"aɪə": 256282,
|
| 190 |
+
"aʊ": 256051,
|
| 191 |
+
"aʊn": 256339,
|
| 192 |
+
"aʊnd": 256372,
|
| 193 |
+
"aʊt": 256186,
|
| 194 |
+
"aʊə": 256349,
|
| 195 |
+
"baɪ̯": 256283,
|
| 196 |
+
"bm̩": 256278,
|
| 197 |
+
"bn̩": 256171,
|
| 198 |
+
"bɐ": 256094,
|
| 199 |
+
"bə": 256159,
|
| 200 |
+
"bəl": 256222,
|
| 201 |
+
"bɝ": 256429,
|
| 202 |
+
"bɹ": 256539,
|
| 203 |
+
"bʁ": 256248,
|
| 204 |
+
"dn̩": 256131,
|
| 205 |
+
"dɐ": 256136,
|
| 206 |
+
"dɔɪ̯": 256592,
|
| 207 |
+
"dən": 256351,
|
| 208 |
+
"dɛ": 256543,
|
| 209 |
+
"dɪŋ": 256433,
|
| 210 |
+
"dʁ": 256356,
|
| 211 |
+
"dʒ": 256187,
|
| 212 |
+
"dʒ": 256197,
|
| 213 |
+
"eɪ": 256027,
|
| 214 |
+
"eɾ": 256033,
|
| 215 |
+
"eɾa": 256366,
|
| 216 |
+
"eɾo": 256273,
|
| 217 |
+
"eə": 256077,
|
| 218 |
+
"eɪ": 256011,
|
| 219 |
+
"eɪd": 256264,
|
| 220 |
+
"eɪk": 256250,
|
| 221 |
+
"eɪl": 256557,
|
| 222 |
+
"eɪm": 256220,
|
| 223 |
+
"eɪn": 256296,
|
| 224 |
+
"eɪnd": 256398,
|
| 225 |
+
"eɪndʒ": 256566,
|
| 226 |
+
"eɪs": 256287,
|
| 227 |
+
"eɪt": 256128,
|
| 228 |
+
"eɪtɪd": 256382,
|
| 229 |
+
"eɪv": 256526,
|
| 230 |
+
"eɪʃən": 256167,
|
| 231 |
+
"fn̩": 256269,
|
| 232 |
+
"ftɐ": 256481,
|
| 233 |
+
"fɔl": 256387,
|
| 234 |
+
"fɔʁ": 256465,
|
| 235 |
+
"fə": 256497,
|
| 236 |
+
"fɛɐ̯": 256524,
|
| 237 |
+
"fʁ": 256426,
|
| 238 |
+
"hatə": 256395,
|
| 239 |
+
"haɪ̯": 256508,
|
| 240 |
+
"haɪ̯t": 256493,
|
| 241 |
+
"hæv": 256191,
|
| 242 |
+
"ið": 256238,
|
| 243 |
+
"iðo": 256445,
|
| 244 |
+
"iɾ": 256489,
|
| 245 |
+
"iə": 256126,
|
| 246 |
+
"jeɾ": 256295,
|
| 247 |
+
"jœʁ": 256589,
|
| 248 |
+
"jɔ̃": 256098,
|
| 249 |
+
"jɛ": 256534,
|
| 250 |
+
"jɛʁ": 256288,
|
| 251 |
+
"jɛ̃": 256200,
|
| 252 |
+
"jʊ": 256309,
|
| 253 |
+
"kaɪ̯t": 256492,
|
| 254 |
+
"ktə": 256265,
|
| 255 |
+
"kœ": 256512,
|
| 256 |
+
"kɑ": 256438,
|
| 257 |
+
"kɔ": 256401,
|
| 258 |
+
"kə": 256263,
|
| 259 |
+
"kɹ": 256317,
|
| 260 |
+
"laŋ": 256487,
|
| 261 |
+
"laɪ̯": 256239,
|
| 262 |
+
"laɪ̯ç": 256571,
|
| 263 |
+
"laʊ̯": 256441,
|
| 264 |
+
"lɐ": 256415,
|
| 265 |
+
"lən": 256272,
|
| 266 |
+
"lɛ": 256344,
|
| 267 |
+
"lɪç": 256088,
|
| 268 |
+
"lɪçn̩": 256443,
|
| 269 |
+
"lɪçə": 256494,
|
| 270 |
+
"l̩": 256130,
|
| 271 |
+
"maɪ̯": 256584,
|
| 272 |
+
"mɑ̃": 256113,
|
| 273 |
+
"mən": 256152,
|
| 274 |
+
"mənt": 256243,
|
| 275 |
+
"mɛ": 256286,
|
| 276 |
+
"mɛn": 256466,
|
| 277 |
+
"mɪt": 256304,
|
| 278 |
+
"m̩": 256205,
|
| 279 |
+
"ndn̩": 256451,
|
| 280 |
+
"ndɐ": 256298,
|
| 281 |
+
"ndə": 256237,
|
| 282 |
+
"noʊ": 256274,
|
| 283 |
+
"ntə": 256377,
|
| 284 |
+
"nt͡s": 256369,
|
| 285 |
+
"nɐ": 256595,
|
| 286 |
+
"nə": 256209,
|
| 287 |
+
"nən": 256189,
|
| 288 |
+
"nəs": 256442,
|
| 289 |
+
"nɛ": 256446,
|
| 290 |
+
"nɪk": 256486,
|
| 291 |
+
"n̩": 256005,
|
| 292 |
+
"oɾ": 256048,
|
| 293 |
+
"oɾa": 256480,
|
| 294 |
+
"oʊ": 256078,
|
| 295 |
+
"pəl": 256555,
|
| 296 |
+
"pɹ": 256225,
|
| 297 |
+
"pʁ": 256569,
|
| 298 |
+
"pʁi": 256536,
|
| 299 |
+
"p͡f": 256416,
|
| 300 |
+
"sjɔ̃": 256448,
|
| 301 |
+
"sn̩": 256280,
|
| 302 |
+
"stn̩": 256260,
|
| 303 |
+
"stɐ": 256410,
|
| 304 |
+
"stə": 256240,
|
| 305 |
+
"tn̩": 256076,
|
| 306 |
+
"tɐ": 256100,
|
| 307 |
+
"tɑ̃": 256585,
|
| 308 |
+
"tə": 256024,
|
| 309 |
+
"tən": 256503,
|
| 310 |
+
"tət": 256462,
|
| 311 |
+
"tɛ": 256161,
|
| 312 |
+
"tɛʁ": 256570,
|
| 313 |
+
"tɪd": 256470,
|
| 314 |
+
"tʁ": 256072,
|
| 315 |
+
"tʁa": 256474,
|
| 316 |
+
"tʃ": 256149,
|
| 317 |
+
"tʃa": 256542,
|
| 318 |
+
"tʃo": 256464,
|
| 319 |
+
"t͡": 256430,
|
| 320 |
+
"t͡s": 256028,
|
| 321 |
+
"t͡si": 256198,
|
| 322 |
+
"t͡si̯o": 256340,
|
| 323 |
+
"t͡sn̩": 256537,
|
| 324 |
+
"t͡su": 256253,
|
| 325 |
+
"tʃ": 256216,
|
| 326 |
+
"uʁ": 256099,
|
| 327 |
+
"vaɪ̯": 256180,
|
| 328 |
+
"vɑ̃": 256544,
|
| 329 |
+
"vɔl": 256467,
|
| 330 |
+
"vɔʁ": 256516,
|
| 331 |
+
"vən": 256551,
|
| 332 |
+
"vɛ": 256097,
|
| 333 |
+
"vɛl": 256432,
|
| 334 |
+
"vɛʁ": 256166,
|
| 335 |
+
"vɛʁdn̩": 256352,
|
| 336 |
+
"vɪs": 256535,
|
| 337 |
+
"vɪʁ": 256562,
|
| 338 |
+
"vʊʁ": 256275,
|
| 339 |
+
"vʊʁdə": 256376,
|
| 340 |
+
"waʁ": 256255,
|
| 341 |
+
"weɾ": 256431,
|
| 342 |
+
"wɛ̃": 256418,
|
| 343 |
+
"wɝ": 256203,
|
| 344 |
+
"xn̩": 256485,
|
| 345 |
+
"xtə": 256576,
|
| 346 |
+
"yʁ": 256125,
|
| 347 |
+
"zaɪ̯nə": 256457,
|
| 348 |
+
"zn̩": 256262,
|
| 349 |
+
"zɐ": 256353,
|
| 350 |
+
"zɔ": 256567,
|
| 351 |
+
"zɔl": 256437,
|
| 352 |
+
"zə": 256182,
|
| 353 |
+
"zɛ": 256400,
|
| 354 |
+
"ækt": 256338,
|
| 355 |
+
"æm": 256299,
|
| 356 |
+
"æp": 256403,
|
| 357 |
+
"æz": 256095,
|
| 358 |
+
"æŋ": 256528,
|
| 359 |
+
"æɫ": 256553,
|
| 360 |
+
"æɹ": 256412,
|
| 361 |
+
"çn̩": 256374,
|
| 362 |
+
"çt": 256323,
|
| 363 |
+
"çə": 256439,
|
| 364 |
+
"ðað": 256341,
|
| 365 |
+
"ðe": 256297,
|
| 366 |
+
"ðo": 256153,
|
| 367 |
+
"ðos": 256495,
|
| 368 |
+
"ðɐ": 256190,
|
| 369 |
+
"ŋg": 256469,
|
| 370 |
+
"ŋk": 256155,
|
| 371 |
+
"œl": 256556,
|
| 372 |
+
"œʁ": 256106,
|
| 373 |
+
"œ̃": 256112,
|
| 374 |
+
"ɐn": 256117,
|
| 375 |
+
"ɐ̯": 256002,
|
| 376 |
+
"ɐ̯t": 256169,
|
| 377 |
+
"ɐ̯tə": 256477,
|
| 378 |
+
"ɑɹ": 256115,
|
| 379 |
+
"ɑ̃": 256006,
|
| 380 |
+
"ɑ̃d": 256217,
|
| 381 |
+
"ɑ̃s": 256148,
|
| 382 |
+
"ɑ̃t": 256246,
|
| 383 |
+
"ɒd": 256506,
|
| 384 |
+
"ɒf": 256435,
|
| 385 |
+
"ɒl": 256160,
|
| 386 |
+
"ɒls": 256348,
|
| 387 |
+
"ɒlsəʊ": 256362,
|
| 388 |
+
"ɒm": 256179,
|
| 389 |
+
"ɒn": 256063,
|
| 390 |
+
"ɒnt": 256578,
|
| 391 |
+
"ɒp": 256360,
|
| 392 |
+
"ɒt": 256092,
|
| 393 |
+
"ɒv": 256022,
|
| 394 |
+
"ɒz": 256080,
|
| 395 |
+
"ɒŋ": 256327,
|
| 396 |
+
"ɒɹ": 256499,
|
| 397 |
+
"ɔk": 256560,
|
| 398 |
+
"ɔl": 256084,
|
| 399 |
+
"ɔm": 256082,
|
| 400 |
+
"ɔmən": 256463,
|
| 401 |
+
"ɔn": 256065,
|
| 402 |
+
"ɔs": 256436,
|
| 403 |
+
"ɔt": 256527,
|
| 404 |
+
"ɔx": 256173,
|
| 405 |
+
"ɔɪ̯": 256086,
|
| 406 |
+
"ɔɹ": 256229,
|
| 407 |
+
"ɔʁ": 256038,
|
| 408 |
+
"ɔʁt": 256223,
|
| 409 |
+
"ɔ̃": 256014,
|
| 410 |
+
"ɔɪ": 256261,
|
| 411 |
+
"əd": 256252,
|
| 412 |
+
"ənd": 256232,
|
| 413 |
+
"əns": 256178,
|
| 414 |
+
"ənt": 256066,
|
| 415 |
+
"ənz": 256335,
|
| 416 |
+
"əs": 256044,
|
| 417 |
+
"əz": 256292,
|
| 418 |
+
"əɹ": 256194,
|
| 419 |
+
"əɹi": 256575,
|
| 420 |
+
"ə": 256008,
|
| 421 |
+
"əl": 256037,
|
| 422 |
+
"əli": 256530,
|
| 423 |
+
"əʊ": 256017,
|
| 424 |
+
"əʊk": 256475,
|
| 425 |
+
"əʊl": 256399,
|
| 426 |
+
"əʊld": 256326,
|
| 427 |
+
"əʊn": 256212,
|
| 428 |
+
"əʊnli": 256488,
|
| 429 |
+
"əʊp": 256586,
|
| 430 |
+
"əʊst": 256385,
|
| 431 |
+
"əʊt": 256541,
|
| 432 |
+
"əʊv": 256420,
|
| 433 |
+
"əʊvɐ": 256591,
|
| 434 |
+
"əʊz": 256285,
|
| 435 |
+
"ɛd": 256127,
|
| 436 |
+
"ɛf": 256491,
|
| 437 |
+
"ɛk": 256154,
|
| 438 |
+
"ɛks": 256422,
|
| 439 |
+
"ɛkt": 256195,
|
| 440 |
+
"ɛl": 256032,
|
| 441 |
+
"ɛlf": 256379,
|
| 442 |
+
"ɛlp": 256479,
|
| 443 |
+
"ɛlt": 256276,
|
| 444 |
+
"ɛm": 256122,
|
| 445 |
+
"ɛn": 256030,
|
| 446 |
+
"ɛnd": 256150,
|
| 447 |
+
"ɛni": 256331,
|
| 448 |
+
"ɛns": 256598,
|
| 449 |
+
"ɛnt": 256105,
|
| 450 |
+
"ɛp": 256449,
|
| 451 |
+
"ɛs": 256054,
|
| 452 |
+
"ɛst": 256124,
|
| 453 |
+
"ɛt": 256050,
|
| 454 |
+
"ɛtʁ": 256565,
|
| 455 |
+
"ɛt͡": 256308,
|
| 456 |
+
"ɛt͡st": 256455,
|
| 457 |
+
"ɛv": 256151,
|
| 458 |
+
"ɛvɐ": 256336,
|
| 459 |
+
"ɛz": 256281,
|
| 460 |
+
"ɛŋ": 256417,
|
| 461 |
+
"ɛɐ̯": 256071,
|
| 462 |
+
"ɛɹ": 256396,
|
| 463 |
+
"ɛɹi": 256363,
|
| 464 |
+
"ɛʁ": 256020,
|
| 465 |
+
"ɛʁn": 256386,
|
| 466 |
+
"ɛ̃": 256059,
|
| 467 |
+
"ɝz": 256206,
|
| 468 |
+
"ɡa": 256347,
|
| 469 |
+
"ɡe": 256201,
|
| 470 |
+
"ɡi": 256471,
|
| 471 |
+
"ɡn̩": 256081,
|
| 472 |
+
"ɡz": 256529,
|
| 473 |
+
"ɡɐ": 256427,
|
| 474 |
+
"ɡə": 256069,
|
| 475 |
+
"ɡɹ": 256371,
|
| 476 |
+
"ɡʁ": 256397,
|
| 477 |
+
"ɡʁo": 256605,
|
| 478 |
+
"ɣa": 256579,
|
| 479 |
+
"ɣo": 256329,
|
| 480 |
+
"ɥi": 256119,
|
| 481 |
+
"ɪd": 256041,
|
| 482 |
+
"ɪdʒ": 256244,
|
| 483 |
+
"ɪf": 256102,
|
| 484 |
+
"ɪk": 256034,
|
| 485 |
+
"ɪks": 256561,
|
| 486 |
+
"ɪkt": 256450,
|
| 487 |
+
"ɪkəl": 256502,
|
| 488 |
+
"ɪl": 256058,
|
| 489 |
+
"ɪm": 256046,
|
| 490 |
+
"ɪmɐ": 256518,
|
| 491 |
+
"ɪn": 256010,
|
| 492 |
+
"ɪnd": 256176,
|
| 493 |
+
"ɪns": 256546,
|
| 494 |
+
"ɪnt": 256109,
|
| 495 |
+
"ɪntʊ": 256434,
|
| 496 |
+
"ɪp": 256207,
|
| 497 |
+
"ɪs": 256040,
|
| 498 |
+
"ɪst": 256068,
|
| 499 |
+
"ɪt": 256013,
|
| 500 |
+
"ɪti": 256234,
|
| 501 |
+
"ɪts": 256228,
|
| 502 |
+
"ɪtəl": 256531,
|
| 503 |
+
"ɪtʃ": 256204,
|
| 504 |
+
"ɪv": 256118,
|
| 505 |
+
"ɪz": 256023,
|
| 506 |
+
"ɪç": 256015,
|
| 507 |
+
"ɪçt": 256096,
|
| 508 |
+
"ɪð": 256108,
|
| 509 |
+
"ɪŋ": 256019,
|
| 510 |
+
"ɪŋk": 256456,
|
| 511 |
+
"ɪŋz": 256583,
|
| 512 |
+
"ɪɡ": 256181,
|
| 513 |
+
"ɪɡn̩": 256316,
|
| 514 |
+
"ɪɡə": 256337,
|
| 515 |
+
"ɪɫ": 256421,
|
| 516 |
+
"ɪɹ": 256392,
|
| 517 |
+
"ɪʁ": 256270,
|
| 518 |
+
"ɪʃ": 256089,
|
| 519 |
+
"ɪʃn̩": 256257,
|
| 520 |
+
"ɪʃə": 256390,
|
| 521 |
+
"ɪʃən": 256301,
|
| 522 |
+
"ɪ̯": 256003,
|
| 523 |
+
"ɫa": 256476,
|
| 524 |
+
"ɫi": 256384,
|
| 525 |
+
"ɫz": 256354,
|
| 526 |
+
"ɹi": 256087,
|
| 527 |
+
"ɹə": 256110,
|
| 528 |
+
"ɹɪ": 256300,
|
| 529 |
+
"ɹɪŋ": 256468,
|
| 530 |
+
"ɾa": 256093,
|
| 531 |
+
"ɾan": 256424,
|
| 532 |
+
"ɾas": 256408,
|
| 533 |
+
"ɾe": 256104,
|
| 534 |
+
"ɾes": 256303,
|
| 535 |
+
"ɾi": 256141,
|
| 536 |
+
"ɾia": 256572,
|
| 537 |
+
"ɾo": 256134,
|
| 538 |
+
"ɾos": 256504,
|
| 539 |
+
"ʁa": 256036,
|
| 540 |
+
"ʁaɪ̯": 256163,
|
| 541 |
+
"ʁaʊ̯": 256219,
|
| 542 |
+
"ʁe": 256170,
|
| 543 |
+
"ʁi": 256061,
|
| 544 |
+
"ʁo": 256174,
|
| 545 |
+
"ʁu": 256473,
|
| 546 |
+
"ʁy": 256306,
|
| 547 |
+
"ʁɐ": 256452,
|
| 548 |
+
"ʁɔ": 256365,
|
| 549 |
+
"ʁə": 256157,
|
| 550 |
+
"ʁən": 256133,
|
| 551 |
+
"ʁɛ": 256090,
|
| 552 |
+
"ʁʊŋ": 256423,
|
| 553 |
+
"ʃa": 256290,
|
| 554 |
+
"ʃaft": 256594,
|
| 555 |
+
"ʃe": 256525,
|
| 556 |
+
"ʃi": 256346,
|
| 557 |
+
"ʃn̩": 256500,
|
| 558 |
+
"ʃp": 256267,
|
| 559 |
+
"ʃt": 256107,
|
| 560 |
+
"ʃta": 256271,
|
| 561 |
+
"ʃtɛl": 256577,
|
| 562 |
+
"ʃən": 256060,
|
| 563 |
+
"ʃənz": 256447,
|
| 564 |
+
"ʃəl": 256590,
|
| 565 |
+
"ʊd": 256129,
|
| 566 |
+
"ʊk": 256314,
|
| 567 |
+
"ʊl": 256532,
|
| 568 |
+
"ʊm": 256139,
|
| 569 |
+
"ʊn": 256156,
|
| 570 |
+
"ʊnt": 256025,
|
| 571 |
+
"ʊntɐ": 256307,
|
| 572 |
+
"ʊs": 256251,
|
| 573 |
+
"ʊt": 256597,
|
| 574 |
+
"ʊŋ": 256070,
|
| 575 |
+
"ʊŋən": 256325,
|
| 576 |
+
"ʊʁ": 256132,
|
| 577 |
+
"ʊʁç": 256294,
|
| 578 |
+
"ʊ̯": 256021,
|
| 579 |
+
"ʌm": 256164,
|
| 580 |
+
"ʌn": 256242,
|
| 581 |
+
"ʌnt": 256425,
|
| 582 |
+
"ʌp": 256302,
|
| 583 |
+
"ʌs": 256364,
|
| 584 |
+
"ʌst": 256268,
|
| 585 |
+
"ʌt": 256123,
|
| 586 |
+
"ʌtʃ": 256342,
|
| 587 |
+
"ʌv": 256378,
|
| 588 |
+
"ʌðɐ": 256332,
|
| 589 |
+
"ʌŋ": 256496,
|
| 590 |
+
"ʎa": 256350,
|
| 591 |
+
"ʎe": 256483,
|
| 592 |
+
"ʏk": 256380,
|
| 593 |
+
"ʏn": 256573,
|
| 594 |
+
"ʏʁ": 256318,
|
| 595 |
+
"ʒe": 256460,
|
| 596 |
+
"ʒi": 256454,
|
| 597 |
+
"ː.": 256241,
|
| 598 |
+
"ːˈ": 256221,
|
| 599 |
+
"ːˌ": 256411,
|
| 600 |
+
"̯o": 256231,
|
| 601 |
+
"͡f": 256313,
|
| 602 |
+
"͡s": 256012,
|
| 603 |
+
"ə": 256029,
|
| 604 |
+
"ən": 256564,
|
| 605 |
+
"ɪ": 256001,
|
| 606 |
+
"ʃ": 256045,
|
| 607 |
+
"ʒ": 256055
|
| 608 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 2097228602327040.0,
|
| 4 |
+
"train_loss": 0.050915672732994244,
|
| 5 |
+
"train_runtime": 738268.7103,
|
| 6 |
+
"train_samples_per_second": 10.388,
|
| 7 |
+
"train_steps_per_second": 0.325
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_logit_softcapping": 50.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"cache_implementation": "hybrid",
|
| 10 |
+
"eos_token_id": 1,
|
| 11 |
+
"final_logit_softcapping": 30.0,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 2304,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 9216,
|
| 18 |
+
"max_position_embeddings": 8192,
|
| 19 |
+
"model_type": "gemma2",
|
| 20 |
+
"num_attention_heads": 8,
|
| 21 |
+
"num_hidden_layers": 26,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"query_pre_attn_scalar": 256,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"sliding_window": 4096,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.1",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 256606
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.52.1",
|
| 8 |
+
"use_cache": false
|
| 9 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b5e987b6ff50d86c9c9bad2d803bb1dd1f10baebc1e4df65fa16f1d275bab3f
|
| 3 |
+
size 4990818208
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5189aa23cd8d9d48e7bce61a6e1a0106a8cda856ccd3c938e84908f96c3790bb
|
| 3 |
+
size 240691728
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5231476224
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 294 |
+
}
|
| 295 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<bos>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<eos>",
|
| 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": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9bc615c6c14973dda6a5058c6ee0d3693d581fa5067b99c2c7af6388101fbb8
|
| 3 |
+
size 34472979
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 2097228602327040.0,
|
| 4 |
+
"train_loss": 0.050915672732994244,
|
| 5 |
+
"train_runtime": 738268.7103,
|
| 6 |
+
"train_samples_per_second": 10.388,
|
| 7 |
+
"train_steps_per_second": 0.325
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:144360cec1f136fe47a8c04783405f9d6a6f86f02e4caaf557091c1f6aebd8e5
|
| 3 |
+
size 7544
|