Duplicate from allenai/OLMo-2-1124-7B-Instruct
Browse filesCo-authored-by: Shengyi Costa Huang <vwxyzjn@users.noreply.huggingface.co>
- .gitattributes +35 -0
- README.md +151 -0
- config.json +27 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +362 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +190 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
README.md
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
base_model:
|
| 7 |
+
- allenai/OLMo-2-1124-7B-DPO
|
| 8 |
+
library_name: transformers
|
| 9 |
+
datasets:
|
| 10 |
+
- allenai/RLVR-GSM
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<img alt="OLMo Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmo2/olmo.png" width="242px">
|
| 14 |
+
|
| 15 |
+
# OLMo-2-1124-7B-Instruct
|
| 16 |
+
|
| 17 |
+
## NOTE: 1/3/2025 UPDATE:
|
| 18 |
+
|
| 19 |
+
Upon the initial release of OLMo-2 models, we realized the post-trained models did not share the pre-tokenization logic that the base models use. As a result, we have trained new post-trained models. The new models are available under the same names as the original models, but we have made the old models available with a postfix "-preview". See [OLMo 2 Preview Post-trained Models](https://huggingface.co/collections/allenai/olmo-2-preview-post-trained-models-6762f662c660962e52de7c96) for the colleciton of the legacy models.
|
| 20 |
+
|
| 21 |
+
## Release Documentation
|
| 22 |
+
|
| 23 |
+
OLMo 2 7B Instruct November 2024 is post-trained variant of the [OLMo-2 7B November 2024](https://huggingface.co/allenai/OLMo2-7B-1124) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](https://huggingface.co/datasets/allenai/tulu-3-sft-olmo-2-mixture) and further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-1124-7b-preference-mix), and finally RLVR training using [this data](https://huggingface.co/datasets/allenai/RLVR-GSM).
|
| 24 |
+
Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
|
| 25 |
+
Check out the [OLMo 2 paper](https://arxiv.org/abs/2501.00656) or [Tülu 3 paper](https://arxiv.org/abs/2411.15124) for more details!
|
| 26 |
+
|
| 27 |
+
OLMo is a series of **O**pen **L**anguage **Mo**dels designed to enable the science of language models.
|
| 28 |
+
These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs (coming soon), and associated training details.
|
| 29 |
+
The core models released in this batch include the following:
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
| **Stage** | **OLMo 2 7B** | **OLMo 2 13B** |
|
| 33 |
+
|----------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|
|
| 34 |
+
| **Base Model** | [allenai/OLMo2-7B-1124](https://huggingface.co/allenai/OLMo2-7B-1124) | [allenai/OLMo-2-13B-1124](https://huggingface.co/allenai/OLMo-2-13B-1124) |
|
| 35 |
+
| **SFT** | [allenai/OLMo-2-1124-7B-SFT](https://huggingface.co/allenai/OLMo-2-1124-7B-SFT) | [allenai/OLMo-2-1124-13B-SFT](https://huggingface.co/allenai/OLMo-2-1124-13B-SFT) |
|
| 36 |
+
| **DPO** | [allenai/OLMo-2-1124-7B-DPO](https://huggingface.co/allenai/OLMo-2-1124-7B-DPO) | [allenai/OLMo-2-1124-13B-DPO](https://huggingface.co/allenai/OLMo-2-1124-13B-DPO) |
|
| 37 |
+
| **Final Models (RLVR)** | [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct) | [allenai/OLMo-2-1124-13B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-13B-Instruct) |
|
| 38 |
+
| **Reward Model (RM)**| [allenai/OLMo-2-1124-7B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM) | [allenai/OLMo-2-1124-13B-RM](https://huggingface.co/allenai/OLMo-2-1124-13B-RM) |
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
## Model description
|
| 43 |
+
|
| 44 |
+
- **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets.
|
| 45 |
+
- **Language(s) (NLP):** Primarily English
|
| 46 |
+
- **License:** Apache 2.0
|
| 47 |
+
- **Finetuned from model:** allenai/OLMo-2-7B-1124-DPO
|
| 48 |
+
|
| 49 |
+
### Model Sources
|
| 50 |
+
|
| 51 |
+
- **Project Page:** https://allenai.org/olmo
|
| 52 |
+
- **Repositories:**
|
| 53 |
+
- Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo
|
| 54 |
+
- Evaluation code: https://github.com/allenai/olmes
|
| 55 |
+
- Further fine-tuning code: https://github.com/allenai/open-instruct
|
| 56 |
+
- **Paper:** https://arxiv.org/abs/2501.00656
|
| 57 |
+
- **Demo:** https://playground.allenai.org/
|
| 58 |
+
|
| 59 |
+
## Installation
|
| 60 |
+
|
| 61 |
+
OLMo 2 will be supported in the next version of Transformers, and you need to install it from the main branch using:
|
| 62 |
+
```bash
|
| 63 |
+
pip install --upgrade git+https://github.com/huggingface/transformers.git
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## Using the model
|
| 67 |
+
|
| 68 |
+
### Loading with HuggingFace
|
| 69 |
+
|
| 70 |
+
To load the model with HuggingFace, use the following snippet:
|
| 71 |
+
```
|
| 72 |
+
from transformers import AutoModelForCausalLM
|
| 73 |
+
|
| 74 |
+
olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B-Instruct")
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
### Chat template
|
| 78 |
+
|
| 79 |
+
The chat template for our models is formatted as:
|
| 80 |
+
```
|
| 81 |
+
<|endoftext|><|user|>\nHow are you doing?\n<|assistant|>\nI'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
|
| 82 |
+
```
|
| 83 |
+
Or with new lines expanded:
|
| 84 |
+
```
|
| 85 |
+
<|endoftext|><|user|>
|
| 86 |
+
How are you doing?
|
| 87 |
+
<|assistant|>
|
| 88 |
+
I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
|
| 89 |
+
```
|
| 90 |
+
It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`.
|
| 91 |
+
|
| 92 |
+
### System prompt
|
| 93 |
+
|
| 94 |
+
In Ai2 demos, we use this system prompt by default:
|
| 95 |
+
```
|
| 96 |
+
You are OLMo 2, a helpful and harmless AI Assistant built by the Allen Institute for AI.
|
| 97 |
+
```
|
| 98 |
+
The model has not been trained with a specific system prompt in mind.
|
| 99 |
+
|
| 100 |
+
### Bias, Risks, and Limitations
|
| 101 |
+
|
| 102 |
+
The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
|
| 103 |
+
See the Falcon 180B model card for an example of this.
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
## Performance
|
| 107 |
+
|
| 108 |
+
| Model | Average | AlpacaEval | BBH | DROP | GSM8k | IFEval | MATH | MMLU | Safety | PopQA | TruthQA |
|
| 109 |
+
|-------|---------|------------|-----|------|--------|---------|------|-------|---------|-------|---------|
|
| 110 |
+
| **Open weights models** |
|
| 111 |
+
| Gemma-2-9B-it | 51.9 | 43.7 | 2.5 | 58.8 | 79.7 | 69.9 | 29.8 | 69.1 | 75.5 | 28.3 | 61.4 |
|
| 112 |
+
| Ministral-8B-Instruct | 52.1 | 31.4 | 56.2 | 56.2 | 80.0 | 56.4 | 40.0 | 68.5 | 56.2 | 20.2 | 55.5 |
|
| 113 |
+
| Mistral-Nemo-Instruct-2407 | 50.9 | 45.8 | 54.6 | 23.6 | 81.4 | 64.5 | 31.9 | 70.0 | 52.7 | 26.9 | 57.7 |
|
| 114 |
+
| Qwen-2.5-7B-Instruct | 57.1 | 29.7 | 25.3 | 54.4 | 83.8 | 74.7 | 69.9 | 76.6 | 75.0 | 18.1 | 63.1 |
|
| 115 |
+
| Llama-3.1-8B-Instruct | 58.9 | 25.8 | 69.7 | 61.7 | 83.4 | 80.6 | 42.5 | 71.3 | 70.2 | 28.4 | 55.1 |
|
| 116 |
+
| Tülu 3 8B | 60.4 | 34.0 | 66.0 | 62.6 | 87.6 | 82.4 | 43.7 | 68.2 | 75.4 | 29.1 | 55.0 |
|
| 117 |
+
| Qwen-2.5-14B-Instruct | 60.8 | 34.6 | 34.0 | 50.5 | 83.9 | 82.4 | 70.6 | 81.1 | 79.3 | 21.1 | 70.8 |
|
| 118 |
+
| **Fully open models** |
|
| 119 |
+
| OLMo-7B-Instruct | 28.2 | 5.2 | 35.3 | 30.7 | 14.3 | 32.2 | 2.1 | 46.3 | 54.0 | 17.1 | 44.5 |
|
| 120 |
+
| OLMo-7B-0424-Instruct | 33.1 | 8.5 | 34.4 | 47.9 | 23.2 | 39.2 | 5.2 | 48.9 | 49.3 | 18.9 | 55.2 |
|
| 121 |
+
| OLMoE-1B-7B-0924-Instruct | 35.5 | 8.5 | 37.2 | 34.3 | 47.2 | 46.2 | 8.4 | 51.6 | 51.6 | 20.6 | 49.1 |
|
| 122 |
+
| MAP-Neo-7B-Instruct | 42.9 | 17.6 | 26.4 | 48.2 | 69.4 | 35.9 | 31.5 | 56.5 | 73.7 | 18.4 | 51.6 |
|
| 123 |
+
| *OLMo-2-7B-SFT* | 50.2 | 10.2 | 49.7 | 59.6 | 74.6 | 66.9 | 25.3 | 61.1 | 82.1 | 23.6 | 48.6 |
|
| 124 |
+
| *OLMo-2-7B-DPO* | 54.2 | 27.9 | 46.7 | 60.2 | 82.6 | 73.0 | 30.3 | 60.8 | 81.0 | 23.5 | 56.0 |
|
| 125 |
+
| *OLMo-2-13B-SFT* | 55.3 | 11.5 | 59.6 | 71.3 | 76.3 | 68.6 | 29.5 | 68.0 | 82.3 | 29.4 | 57.1 |
|
| 126 |
+
| *OLMo-2-13B-DPO* | 60.6 | 38.3 | 57.9 | 71.5 | 82.3 | 80.2 | 35.2 | 67.9 | 79.7 | 29.0 | 63.9 |
|
| 127 |
+
| **OLMo-2-7B-1124–Instruct** | 54.8 | 29.1 | 46.6 | 60.5 | 85.1 | 72.3 | 32.5 | 61.3 | 80.6 | 23.2 | 56.5 |
|
| 128 |
+
| **OLMo-2-13B-1124-Instruct** | 62.0 | 39.5 | 58.8 | 71.5 | 87.4 | 82.6 | 39.2 | 68.5 | 79.1 | 28.8 | 64.3 |
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
## License and use
|
| 132 |
+
|
| 133 |
+
OLMo 2 is licensed under the Apache 2.0 license.
|
| 134 |
+
OLMo 2 is intended for research and educational use.
|
| 135 |
+
For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
|
| 136 |
+
This model has been fine-tuned using a dataset mix with outputs generated from third party models and are subject to additional terms: [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|
| 137 |
+
|
| 138 |
+
## Citation
|
| 139 |
+
|
| 140 |
+
```bibtex
|
| 141 |
+
@article{olmo20242olmo2furious,
|
| 142 |
+
title={2 OLMo 2 Furious},
|
| 143 |
+
author={Team OLMo and Pete Walsh and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Shane Arora and Akshita Bhagia and Yuling Gu and Shengyi Huang and Matt Jordan and Nathan Lambert and Dustin Schwenk and Oyvind Tafjord and Taira Anderson and David Atkinson and Faeze Brahman and Christopher Clark and Pradeep Dasigi and Nouha Dziri and Michal Guerquin and Hamish Ivison and Pang Wei Koh and Jiacheng Liu and Saumya Malik and William Merrill and Lester James V. Miranda and Jacob Morrison and Tyler Murray and Crystal Nam and Valentina Pyatkin and Aman Rangapur and Michael Schmitz and Sam Skjonsberg and David Wadden and Christopher Wilhelm and Michael Wilson and Luke Zettlemoyer and Ali Farhadi and Noah A. Smith and Hannaneh Hajishirzi},
|
| 144 |
+
year={2024},
|
| 145 |
+
eprint={2501.00656},
|
| 146 |
+
archivePrefix={arXiv},
|
| 147 |
+
primaryClass={cs.CL},
|
| 148 |
+
url={https://arxiv.org/abs/2501.00656},
|
| 149 |
+
}
|
| 150 |
+
```
|
| 151 |
+
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/open_instruct_dev",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Olmo2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"eos_token_id": 100257,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "olmo2",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 32,
|
| 18 |
+
"pad_token_id": 100277,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 500000,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.47.0.dev0",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 100257,
|
| 4 |
+
"pad_token_id": 100277,
|
| 5 |
+
"transformers_version": "4.47.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ae91e1171f1f1753b23df3a5a6740d89da377932b33a1661bb7485d6ec530e
|
| 3 |
+
size 4970591184
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d41b81fe0d7e4c1d673a77beded5ee77080e39d6a6940b523e82f61eaa1dcbd
|
| 3 |
+
size 4981161496
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51d701cc400703094ae4b6434b067ee8810056170ce4703e93b2f5b2cb93a51d
|
| 3 |
+
size 4645523448
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,362 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14597234688
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 141 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 142 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 143 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 144 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 151 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 298 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 299 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 300 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 301 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 302 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 303 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 306 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 308 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 309 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 310 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 311 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 312 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 313 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 314 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 315 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 316 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 317 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 318 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 319 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 320 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 321 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 322 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 323 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 324 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 325 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 326 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 327 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 328 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 329 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 330 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 331 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 332 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 333 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 334 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 335 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 336 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 337 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 338 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 339 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 340 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 341 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 342 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 343 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 344 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 345 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 346 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 347 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 348 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 349 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 350 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 351 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 352 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 353 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 354 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 355 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 356 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 357 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 358 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 359 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 360 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 361 |
+
}
|
| 362 |
+
}
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
|
| 183 |
+
"clean_up_tokenization_spaces": false,
|
| 184 |
+
"eos_token": "<|endoftext|>",
|
| 185 |
+
"extra_special_tokens": {},
|
| 186 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 187 |
+
"pad_token": "<|pad|>",
|
| 188 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 189 |
+
"unk_token": "<|endoftext|>"
|
| 190 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|