Upload folder using huggingface_hub
Browse files- README.md +466 -0
- config.json +90 -0
- generation_config.json +8 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +330 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +783 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,466 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- ibm-granite/granite-4.0-micro-base
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- language
|
| 8 |
+
- unsloth
|
| 9 |
+
- granite-4.0
|
| 10 |
+
---
|
| 11 |
+
<div>
|
| 12 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 13 |
+
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
| 14 |
+
</p>
|
| 15 |
+
<div style="display: flex; gap: 5px; align-items: center; ">
|
| 16 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 17 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 18 |
+
</a>
|
| 19 |
+
<a href="https://discord.gg/unsloth">
|
| 20 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 21 |
+
</a>
|
| 22 |
+
<a href="https://docs.unsloth.ai/">
|
| 23 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 24 |
+
</a>
|
| 25 |
+
</div>
|
| 26 |
+
</div>
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
# Granite-4.0-Micro-Base
|
| 30 |
+
|
| 31 |
+
**Model Summary:**
|
| 32 |
+
Granite-4.0-Micro-Base is a decoder-only, long-context language model designed for a wide range of text-to-text generation tasks. It also supports Fill-in-the-Middle (FIM) code completion through the use of specialized prefix and suffix tokens. The model is trained from scratch on approximately 15 trillion tokens following a four-stage training strategy: 10 trillion tokens in the first stage, 2 trillion in the second, another 2 trillion in the third, and 0.5 trillion in the final stage.
|
| 33 |
+
|
| 34 |
+
- **Developers:** Granite Team, IBM
|
| 35 |
+
- **HF Collection:** [Granite 4.0 Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-40-language-models-6811a18b820ef362d9e5a82c)
|
| 36 |
+
- **GitHub Repository:** [ibm-granite/granite-4.0-language-models](https://github.com/ibm-granite/granite-4.0-language-models)
|
| 37 |
+
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
|
| 38 |
+
- **Release Date**: October 2nd, 2025
|
| 39 |
+
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
| 40 |
+
|
| 41 |
+
**Supported Languages:**
|
| 42 |
+
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.0 models for languages beyond these languages.
|
| 43 |
+
|
| 44 |
+
**Intended Use:**
|
| 45 |
+
Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, code-completion (including FIM), and long-context generation tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.
|
| 46 |
+
|
| 47 |
+
**Generation:**
|
| 48 |
+
This is a simple example of how to use Granite-4.0-Micro-Base model.
|
| 49 |
+
|
| 50 |
+
Install the following libraries:
|
| 51 |
+
|
| 52 |
+
```shell
|
| 53 |
+
pip install torch torchvision torchaudio
|
| 54 |
+
pip install accelerate
|
| 55 |
+
pip install transformers
|
| 56 |
+
```
|
| 57 |
+
Then, copy the code snippet below to run the example.
|
| 58 |
+
|
| 59 |
+
```python
|
| 60 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 61 |
+
device = "cuda"
|
| 62 |
+
|
| 63 |
+
model_path = "ibm-granite/granite-4.0-h-micro-base"
|
| 64 |
+
|
| 65 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 66 |
+
# drop device_map if running on CPU
|
| 67 |
+
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
|
| 68 |
+
model.eval()
|
| 69 |
+
# change input text as desired
|
| 70 |
+
input_text = "The capital of France is"
|
| 71 |
+
# tokenize the text
|
| 72 |
+
input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
|
| 73 |
+
# generate output tokens
|
| 74 |
+
output = model.generate(**input_tokens, max_length=10)
|
| 75 |
+
# decode output tokens into text
|
| 76 |
+
output = tokenizer.batch_decode(output)
|
| 77 |
+
# print output
|
| 78 |
+
print(output[0])
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
Expected output:
|
| 82 |
+
```shell
|
| 83 |
+
The capital of France is Paris.
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
**Evaluation Results:**
|
| 87 |
+
|
| 88 |
+
<table>
|
| 89 |
+
<!-- <caption><b> All Results</b></caption> -->
|
| 90 |
+
<thead>
|
| 91 |
+
<tr>
|
| 92 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
|
| 93 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Metric</th>
|
| 94 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
|
| 95 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
|
| 96 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
|
| 97 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
|
| 98 |
+
</tr>
|
| 99 |
+
</thead>
|
| 100 |
+
<tbody>
|
| 101 |
+
<tr>
|
| 102 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 103 |
+
General Tasks
|
| 104 |
+
</td>
|
| 105 |
+
</tr>
|
| 106 |
+
<tr>
|
| 107 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU</td>
|
| 108 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 109 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">66.47</td>
|
| 110 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.43</td>
|
| 111 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">68.90</td>
|
| 112 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.85</td>
|
| 113 |
+
</tr>
|
| 114 |
+
<tr>
|
| 115 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU-Pro</td>
|
| 116 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot,CoT</td>
|
| 117 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">37.16</td>
|
| 118 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">34.03</td>
|
| 119 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">35.47</td>
|
| 120 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">48.94</td>
|
| 121 |
+
</tr>
|
| 122 |
+
<tr>
|
| 123 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BBH</td>
|
| 124 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot, CoT</td>
|
| 125 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">63.84</td>
|
| 126 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">57.65</td>
|
| 127 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">59.67</td>
|
| 128 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.84</td>
|
| 129 |
+
</tr>
|
| 130 |
+
<tr>
|
| 131 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AGI EVAL</td>
|
| 132 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot</td>
|
| 133 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">54.32</td>
|
| 134 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">54.59</td>
|
| 135 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">53.69</td>
|
| 136 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.05</td>
|
| 137 |
+
</tr>
|
| 138 |
+
<tr>
|
| 139 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DROP</td>
|
| 140 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 141 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">66.04</td>
|
| 142 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.44</td>
|
| 143 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.92</td>
|
| 144 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">74.69</td>
|
| 145 |
+
</tr>
|
| 146 |
+
<tr>
|
| 147 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 148 |
+
Math Tasks
|
| 149 |
+
</td>
|
| 150 |
+
</tr>
|
| 151 |
+
<tr>
|
| 152 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM8K</td>
|
| 153 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
|
| 154 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">72.93</td>
|
| 155 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.76</td>
|
| 156 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">72.55</td>
|
| 157 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">82.11</td>
|
| 158 |
+
</tr>
|
| 159 |
+
<tr>
|
| 160 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Minerva Math</td>
|
| 161 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">4-shot</td>
|
| 162 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">38</td>
|
| 163 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">39.7</td>
|
| 164 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">40.34</td>
|
| 165 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">46.28</td>
|
| 166 |
+
</tr>
|
| 167 |
+
<tr>
|
| 168 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 169 |
+
Code Tasks
|
| 170 |
+
</td>
|
| 171 |
+
</tr>
|
| 172 |
+
<tr>
|
| 173 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval </td>
|
| 174 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1 [StarCoder Prompt]</td>
|
| 175 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">76.19</td>
|
| 176 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73.72</td>
|
| 177 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">77.59</td>
|
| 178 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83.66</td>
|
| 179 |
+
</tr>
|
| 180 |
+
<tr>
|
| 181 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval</td>
|
| 182 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 183 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">59.76</td>
|
| 184 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.73</td>
|
| 185 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.34</td>
|
| 186 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">76.22</td>
|
| 187 |
+
</tr>
|
| 188 |
+
<tr>
|
| 189 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval+</td>
|
| 190 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 191 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">54.27</td>
|
| 192 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.07</td>
|
| 193 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.02</td>
|
| 194 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">69.51</td>
|
| 195 |
+
</tr>
|
| 196 |
+
<tr>
|
| 197 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP</td>
|
| 198 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 199 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">81.48</td>
|
| 200 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">74.87</td>
|
| 201 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.48</td>
|
| 202 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83.07</td>
|
| 203 |
+
</tr>
|
| 204 |
+
<tr>
|
| 205 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP+</td>
|
| 206 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 207 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.25</td>
|
| 208 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.23</td>
|
| 209 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">68.78</td>
|
| 210 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.37</td>
|
| 211 |
+
</tr>
|
| 212 |
+
<tr>
|
| 213 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 214 |
+
Multilingual Tasks
|
| 215 |
+
</td>
|
| 216 |
+
</tr>
|
| 217 |
+
<tr>
|
| 218 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
|
| 219 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 220 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">56.59</td>
|
| 221 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">58.5</td>
|
| 222 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.77</td>
|
| 223 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.18</td>
|
| 224 |
+
</tr>
|
| 225 |
+
<tr>
|
| 226 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
|
| 227 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 228 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">51.77</td>
|
| 229 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">52.16</td>
|
| 230 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">53.78</td>
|
| 231 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.04</td>
|
| 232 |
+
</tr>
|
| 233 |
+
<tr>
|
| 234 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
|
| 235 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
|
| 236 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">58.48</td>
|
| 237 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">47.04</td>
|
| 238 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">54.64</td>
|
| 239 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">65.2</td>
|
| 240 |
+
</tr>
|
| 241 |
+
</tbody></table>
|
| 242 |
+
|
| 243 |
+
|
| 244 |
+
<table>
|
| 245 |
+
<caption><b>Multilingual Benchmarks and thr included languages:</b></caption>
|
| 246 |
+
<thead>
|
| 247 |
+
<tr>
|
| 248 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
|
| 249 |
+
<th style="text-align:left; background-color: #001d6c; color: white;"># Langs</th>
|
| 250 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Languages</th>
|
| 251 |
+
</tr>
|
| 252 |
+
</thead>
|
| 253 |
+
<tbody>
|
| 254 |
+
<tr>
|
| 255 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
|
| 256 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">11</td>
|
| 257 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ar, de, en, es, fr, ja, ko, pt, zh, bn, hi</td>
|
| 258 |
+
</tr>
|
| 259 |
+
<tr>
|
| 260 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
|
| 261 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">14</td>
|
| 262 |
+
<!-- <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hindi, bengali, tamil, telugu, arabic, german, spanish, french, italian, japanese, korean, dutch, portuguese, chinese</td> -->
|
| 263 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hi, bn, ta, te, ar, de, es, fr, it, ja, ko, nl, pt, zh</td>
|
| 264 |
+
|
| 265 |
+
</tr>
|
| 266 |
+
<tr>
|
| 267 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
|
| 268 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">5</td>
|
| 269 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">en, es, fr, ja, zh</td>
|
| 270 |
+
</tr>
|
| 271 |
+
</tbody>
|
| 272 |
+
</table>
|
| 273 |
+
|
| 274 |
+
|
| 275 |
+
**Model Architecture:**
|
| 276 |
+
|
| 277 |
+
Granite-4.0-Micro-Base is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA, RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings.
|
| 278 |
+
|
| 279 |
+
<table>
|
| 280 |
+
<thead>
|
| 281 |
+
<tr>
|
| 282 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Model</th>
|
| 283 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
|
| 284 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
|
| 285 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
|
| 286 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
|
| 287 |
+
</tr></thead>
|
| 288 |
+
<tbody>
|
| 289 |
+
<tr>
|
| 290 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Embedding size</td>
|
| 291 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">2560</td>
|
| 292 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2048</td>
|
| 293 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">1536</td>
|
| 294 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4096</td>
|
| 295 |
+
</tr>
|
| 296 |
+
<tr>
|
| 297 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of layers</td>
|
| 298 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">40 attention</td>
|
| 299 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
|
| 300 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
|
| 301 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
|
| 302 |
+
</tr>
|
| 303 |
+
<tr>
|
| 304 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Attention head size</td>
|
| 305 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">64</td>
|
| 306 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 307 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 308 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 309 |
+
</tr>
|
| 310 |
+
<tr>
|
| 311 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of attention heads</td>
|
| 312 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">40</td>
|
| 313 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
|
| 314 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">12</td>
|
| 315 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
|
| 316 |
+
</tr>
|
| 317 |
+
<tr>
|
| 318 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of KV heads</td>
|
| 319 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">8</td>
|
| 320 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
|
| 321 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4</td>
|
| 322 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
|
| 323 |
+
</tr>
|
| 324 |
+
<tr>
|
| 325 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Mamba2 state size</td>
|
| 326 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">-</td>
|
| 327 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 328 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 329 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 330 |
+
</tr>
|
| 331 |
+
<tr>
|
| 332 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of Mamba2 heads</td>
|
| 333 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">-</td>
|
| 334 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 335 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">48</td>
|
| 336 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 337 |
+
</tr>
|
| 338 |
+
|
| 339 |
+
<tr>
|
| 340 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">MLP / Shared expert hidden size</td>
|
| 341 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">8192</td>
|
| 342 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
|
| 343 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">1024</td>
|
| 344 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">1536</td>
|
| 345 |
+
</tr>
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
<tr>
|
| 349 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Num. Experts</td>
|
| 350 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">-</td>
|
| 351 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 352 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 353 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">72</td>
|
| 354 |
+
</tr>
|
| 355 |
+
<tr>
|
| 356 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Num. active Experts</td>
|
| 357 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">-</td>
|
| 358 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 359 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">6</td>
|
| 360 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
|
| 361 |
+
</tr>
|
| 362 |
+
<tr>
|
| 363 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Expert hidden size</td>
|
| 364 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">-</td>
|
| 365 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 366 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">512</td>
|
| 367 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">768</td>
|
| 368 |
+
</tr>
|
| 369 |
+
|
| 370 |
+
<tr>
|
| 371 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">MLP activation</td>
|
| 372 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">SwiGLU</td>
|
| 373 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 374 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 375 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 376 |
+
</tr>
|
| 377 |
+
|
| 378 |
+
<tr>
|
| 379 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Sequence length</td>
|
| 380 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">128K</td>
|
| 381 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 382 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 383 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 384 |
+
</tr>
|
| 385 |
+
<tr>
|
| 386 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Position embedding</td>
|
| 387 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">RoPE</td>
|
| 388 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
|
| 389 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
|
| 390 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
|
| 391 |
+
</tr>
|
| 392 |
+
<tr>
|
| 393 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;"># Parameters</td>
|
| 394 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">3B</td>
|
| 395 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 396 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">7B</td>
|
| 397 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32B</td>
|
| 398 |
+
</tr>
|
| 399 |
+
<tr>
|
| 400 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;"># Active parameters</td>
|
| 401 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">3B</td>
|
| 402 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 403 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">1B</td>
|
| 404 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">9B</td>
|
| 405 |
+
</tr>
|
| 406 |
+
</tbody></table>
|
| 407 |
+
|
| 408 |
+
|
| 409 |
+
**Training Data:** This model is trained on a mix of open source and proprietary data following a four-stage training strategy.
|
| 410 |
+
|
| 411 |
+
<table>
|
| 412 |
+
<thead>
|
| 413 |
+
<tr>
|
| 414 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Stage</th>
|
| 415 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Characteristics</th>
|
| 416 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
|
| 417 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
|
| 418 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
|
| 419 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
|
| 420 |
+
</tr></thead>
|
| 421 |
+
<tbody>
|
| 422 |
+
<tr>
|
| 423 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">I</td>
|
| 424 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">General mixture of training data, warmup, and power scheduler for learning rate.</td>
|
| 425 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">10</td>
|
| 426 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
|
| 427 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">15</td>
|
| 428 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">15</td>
|
| 429 |
+
</tr>
|
| 430 |
+
<tr>
|
| 431 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">II</td>
|
| 432 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">General mixture of training data with higher percentages of code and math with power scheduler for learning rate.</td>
|
| 433 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">2</td>
|
| 434 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">5</td>
|
| 435 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">5</td>
|
| 436 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">5</td>
|
| 437 |
+
</tr>
|
| 438 |
+
<tr>
|
| 439 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">III</td>
|
| 440 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">High quality training data, exponential decay of learning rate.</td>
|
| 441 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">2</td>
|
| 442 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
|
| 443 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
|
| 444 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
|
| 445 |
+
</tr>
|
| 446 |
+
<tr>
|
| 447 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">IV</td>
|
| 448 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">High quality training data, linear decay to zero for learning rate.</td>
|
| 449 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">0.5</td>
|
| 450 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
|
| 451 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
|
| 452 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
|
| 453 |
+
</tr>
|
| 454 |
+
</tbody></table>
|
| 455 |
+
|
| 456 |
+
|
| 457 |
+
**Infrastructure:**
|
| 458 |
+
We trained the Granite 4.0 Language Models utilizing an NVIDIA GB200 NVL72 cluster hosted in CoreWeave. Intra-rack communication occurs via the 72-GPU NVLink domain, and a non-blocking, full Fat-Tree NDR 400 Gb/s InfiniBand network provides inter-rack communication. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.
|
| 459 |
+
|
| 460 |
+
**Ethical Considerations and Limitations:**
|
| 461 |
+
The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. Granite-4.0-Micro-Base model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-4.0-Micro-Base model with ethical intentions and in a responsible way.
|
| 462 |
+
|
| 463 |
+
**Resources**
|
| 464 |
+
- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
|
| 465 |
+
- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
|
| 466 |
+
- 💡 Learn about the latest Granite learning resources: https://github.com/ibm-granite-community/
|
config.json
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteMoeHybridForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.015625,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"torch_dtype": "bfloat16",
|
| 10 |
+
"embedding_multiplier": 12,
|
| 11 |
+
"eos_token_id": 100257,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2560,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"attention",
|
| 18 |
+
"attention",
|
| 19 |
+
"attention",
|
| 20 |
+
"attention",
|
| 21 |
+
"attention",
|
| 22 |
+
"attention",
|
| 23 |
+
"attention",
|
| 24 |
+
"attention",
|
| 25 |
+
"attention",
|
| 26 |
+
"attention",
|
| 27 |
+
"attention",
|
| 28 |
+
"attention",
|
| 29 |
+
"attention",
|
| 30 |
+
"attention",
|
| 31 |
+
"attention",
|
| 32 |
+
"attention",
|
| 33 |
+
"attention",
|
| 34 |
+
"attention",
|
| 35 |
+
"attention",
|
| 36 |
+
"attention",
|
| 37 |
+
"attention",
|
| 38 |
+
"attention",
|
| 39 |
+
"attention",
|
| 40 |
+
"attention",
|
| 41 |
+
"attention",
|
| 42 |
+
"attention",
|
| 43 |
+
"attention",
|
| 44 |
+
"attention",
|
| 45 |
+
"attention",
|
| 46 |
+
"attention",
|
| 47 |
+
"attention",
|
| 48 |
+
"attention",
|
| 49 |
+
"attention",
|
| 50 |
+
"attention",
|
| 51 |
+
"attention",
|
| 52 |
+
"attention",
|
| 53 |
+
"attention",
|
| 54 |
+
"attention",
|
| 55 |
+
"attention",
|
| 56 |
+
"attention"
|
| 57 |
+
],
|
| 58 |
+
"logits_scaling": 10,
|
| 59 |
+
"mamba_chunk_size": 256,
|
| 60 |
+
"mamba_conv_bias": true,
|
| 61 |
+
"mamba_d_conv": 4,
|
| 62 |
+
"mamba_d_head": 40,
|
| 63 |
+
"mamba_d_state": 256,
|
| 64 |
+
"mamba_expand": 2,
|
| 65 |
+
"mamba_n_groups": 1,
|
| 66 |
+
"mamba_n_heads": 128,
|
| 67 |
+
"mamba_proj_bias": false,
|
| 68 |
+
"max_position_embeddings": 131072,
|
| 69 |
+
"model_type": "granitemoehybrid",
|
| 70 |
+
"normalization_function": "rmsnorm",
|
| 71 |
+
"num_attention_heads": 40,
|
| 72 |
+
"num_experts_per_tok": 0,
|
| 73 |
+
"num_hidden_layers": 40,
|
| 74 |
+
"num_key_value_heads": 8,
|
| 75 |
+
"num_local_experts": 0,
|
| 76 |
+
"output_router_logits": false,
|
| 77 |
+
"pad_token_id": 100256,
|
| 78 |
+
"position_embedding_type": "rope",
|
| 79 |
+
"residual_multiplier": 0.22,
|
| 80 |
+
"rms_norm_eps": 1e-05,
|
| 81 |
+
"rope_scaling": null,
|
| 82 |
+
"rope_theta": 10000000,
|
| 83 |
+
"router_aux_loss_coef": 0.01,
|
| 84 |
+
"shared_intermediate_size": 8192,
|
| 85 |
+
"tie_word_embeddings": true,
|
| 86 |
+
"transformers_version": "4.56.2",
|
| 87 |
+
"unsloth_fixed": true,
|
| 88 |
+
"use_cache": true,
|
| 89 |
+
"vocab_size": 100352
|
| 90 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"max_length": 131072,
|
| 6 |
+
"pad_token_id": 100256,
|
| 7 |
+
"transformers_version": "4.56.2"
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75418829cdcadec6a9a4cab2ee0e420bedffdc97f2da1875e9f6f836a1defd36
|
| 3 |
+
size 4918145376
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d0e185ab087789816189a907861ad609e2c1be814f682c75ccd14703229dba6
|
| 3 |
+
size 1887565800
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3402836480,
|
| 4 |
+
"total_size": 6805672960
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.15.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.16.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.16.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.17.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.17.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.18.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.18.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.19.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.19.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.20.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.20.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.21.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.21.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.22.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.22.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.23.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.23.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.24.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.24.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.25.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.25.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.26.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.26.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.27.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.27.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.28.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.28.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.29.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.29.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.30.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.30.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.31.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.31.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.32.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.32.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.33.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.33.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.34.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.34.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.35.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.35.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.36.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.36.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.37.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.37.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.38.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.38.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.39.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.39.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 329 |
+
}
|
| 330 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|end_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 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
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"100256": {
|
| 6 |
+
"content": "<|pad|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"100257": {
|
| 14 |
+
"content": "<|end_of_text|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"100258": {
|
| 22 |
+
"content": "<|fim_prefix|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"100259": {
|
| 30 |
+
"content": "<|fim_middle|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"100260": {
|
| 38 |
+
"content": "<|fim_suffix|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"100261": {
|
| 46 |
+
"content": "<|fim_pad|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"100262": {
|
| 54 |
+
"content": "<|filename|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"100263": {
|
| 62 |
+
"content": "<|reponame|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"100264": {
|
| 70 |
+
"content": "<|start_of_role|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"100265": {
|
| 78 |
+
"content": "<|end_of_role|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"100266": {
|
| 86 |
+
"content": "<|unused_1|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"100267": {
|
| 94 |
+
"content": "<|start_of_plugin|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"100268": {
|
| 102 |
+
"content": "<|end_of_plugin|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"100269": {
|
| 110 |
+
"content": "<|unk|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"100270": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"100271": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"100272": {
|
| 134 |
+
"content": "<tool_response>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"100273": {
|
| 142 |
+
"content": "</tool_response>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"100274": {
|
| 150 |
+
"content": "<think>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"100275": {
|
| 158 |
+
"content": "</think>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"100276": {
|
| 166 |
+
"content": "<think_on>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"100277": {
|
| 174 |
+
"content": "<think_off>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"100278": {
|
| 182 |
+
"content": "<schema>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"100279": {
|
| 190 |
+
"content": "</schema>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"100280": {
|
| 198 |
+
"content": "<tools>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"100281": {
|
| 206 |
+
"content": "</tools>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"100282": {
|
| 214 |
+
"content": "<documents>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"100283": {
|
| 222 |
+
"content": "</documents>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"100284": {
|
| 230 |
+
"content": "<|unused_15|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"100285": {
|
| 238 |
+
"content": "<|unused_16|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"100286": {
|
| 246 |
+
"content": "<|unused_17|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"100287": {
|
| 254 |
+
"content": "<|unused_18|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"100288": {
|
| 262 |
+
"content": "<|unused_19|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"100289": {
|
| 270 |
+
"content": "<|unused_20|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"100290": {
|
| 278 |
+
"content": "<|unused_21|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"100291": {
|
| 286 |
+
"content": "<|unused_22|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"100292": {
|
| 294 |
+
"content": "<|unused_23|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"100293": {
|
| 302 |
+
"content": "<|unused_24|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"100294": {
|
| 310 |
+
"content": "<|unused_25|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"100295": {
|
| 318 |
+
"content": "<|unused_26|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"100296": {
|
| 326 |
+
"content": "<|unused_27|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"100297": {
|
| 334 |
+
"content": "<|unused_28|>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"100298": {
|
| 342 |
+
"content": "<|unused_29|>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"100299": {
|
| 350 |
+
"content": "<|unused_30|>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"100300": {
|
| 358 |
+
"content": "<|unused_31|>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"100301": {
|
| 366 |
+
"content": "<|unused_32|>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"100302": {
|
| 374 |
+
"content": "<|unused_33|>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"100303": {
|
| 382 |
+
"content": "<|unused_34|>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"100304": {
|
| 390 |
+
"content": "<|unused_35|>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"100305": {
|
| 398 |
+
"content": "<|unused_36|>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"100306": {
|
| 406 |
+
"content": "<|unused_37|>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"100307": {
|
| 414 |
+
"content": "<|unused_38|>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"100308": {
|
| 422 |
+
"content": "<|unused_39|>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"100309": {
|
| 430 |
+
"content": "<|unused_40|>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"100310": {
|
| 438 |
+
"content": "<|unused_41|>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"100311": {
|
| 446 |
+
"content": "<|unused_42|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"100312": {
|
| 454 |
+
"content": "<|unused_43|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"100313": {
|
| 462 |
+
"content": "<|unused_44|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"100314": {
|
| 470 |
+
"content": "<|unused_45|>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"100315": {
|
| 478 |
+
"content": "<|unused_46|>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"100316": {
|
| 486 |
+
"content": "<|unused_47|>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"100317": {
|
| 494 |
+
"content": "<|unused_48|>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"100318": {
|
| 502 |
+
"content": "<|unused_49|>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"100319": {
|
| 510 |
+
"content": "<|unused_50|>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"100320": {
|
| 518 |
+
"content": "<|unused_51|>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"100321": {
|
| 526 |
+
"content": "<|unused_52|>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"100322": {
|
| 534 |
+
"content": "<|unused_53|>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"100323": {
|
| 542 |
+
"content": "<|unused_54|>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"100324": {
|
| 550 |
+
"content": "<|unused_55|>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"100325": {
|
| 558 |
+
"content": "<|unused_56|>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"100326": {
|
| 566 |
+
"content": "<|unused_57|>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"100327": {
|
| 574 |
+
"content": "<|unused_58|>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"100328": {
|
| 582 |
+
"content": "<|unused_59|>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"100329": {
|
| 590 |
+
"content": "<|unused_60|>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"100330": {
|
| 598 |
+
"content": "<|unused_61|>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"100331": {
|
| 606 |
+
"content": "<|unused_62|>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"100332": {
|
| 614 |
+
"content": "<|unused_63|>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"100333": {
|
| 622 |
+
"content": "<|unused_64|>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"100334": {
|
| 630 |
+
"content": "<|unused_65|>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"100335": {
|
| 638 |
+
"content": "<|unused_66|>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"100336": {
|
| 646 |
+
"content": "<|unused_67|>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"100337": {
|
| 654 |
+
"content": "<|unused_68|>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"100338": {
|
| 662 |
+
"content": "<|unused_69|>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"100339": {
|
| 670 |
+
"content": "<|unused_70|>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"100340": {
|
| 678 |
+
"content": "<|unused_71|>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"100341": {
|
| 686 |
+
"content": "<|unused_72|>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"100342": {
|
| 694 |
+
"content": "<|unused_73|>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"100343": {
|
| 702 |
+
"content": "<|unused_74|>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"100344": {
|
| 710 |
+
"content": "<|unused_75|>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"100345": {
|
| 718 |
+
"content": "<|unused_76|>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"100346": {
|
| 726 |
+
"content": "<|unused_77|>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"100347": {
|
| 734 |
+
"content": "<|unused_78|>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"100348": {
|
| 742 |
+
"content": "<|unused_79|>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"100349": {
|
| 750 |
+
"content": "<|unused_80|>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"100350": {
|
| 758 |
+
"content": "<|unused_81|>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"100351": {
|
| 766 |
+
"content": "<|unused_82|>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
}
|
| 773 |
+
},
|
| 774 |
+
"bos_token": "<|end_of_text|>",
|
| 775 |
+
"clean_up_tokenization_spaces": false,
|
| 776 |
+
"eos_token": "<|end_of_text|>",
|
| 777 |
+
"extra_special_tokens": {},
|
| 778 |
+
"model_max_length": 131072,
|
| 779 |
+
"pad_token": "<|pad|>",
|
| 780 |
+
"padding_side": "left",
|
| 781 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 782 |
+
"unk_token": "<|unk|>"
|
| 783 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|