Add files using upload-large-folder tool
Browse files- README.md +611 -0
- chat_template.jinja +118 -0
- config.json +89 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +594 -0
- model.sig +1 -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 +1,611 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- language
|
| 6 |
+
- granite-4.0
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
[](https://mot.isitopen.ai/model/1161)
|
| 10 |
+
|
| 11 |
+
# Granite-4.0-H-Tiny
|
| 12 |
+
|
| 13 |
+
📣 **Update [10-07-2025]:** Added a *default system prompt* to the chat template to guide the model towards more *professional, accurate, and safe* responses.
|
| 14 |
+
|
| 15 |
+
**Model Summary:**
|
| 16 |
+
Granite-4.0-H-Tiny is a 7B parameter long-context instruct model finetuned from *Granite-4.0-H-Tiny-Base* using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. Granite 4.0 instruct models feature improved *instruction following (IF)* and *tool-calling* capabilities, making them more effective in enterprise applications.
|
| 17 |
+
|
| 18 |
+
- **Developers:** Granite Team, IBM
|
| 19 |
+
- **HF Collection:** [Granite 4.0 Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-40-language-models-6811a18b820ef362d9e5a82c)
|
| 20 |
+
- **GitHub Repository:** [ibm-granite/granite-4.0-language-models](https://github.com/ibm-granite/granite-4.0-language-models)
|
| 21 |
+
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
|
| 22 |
+
- **Release Date**: October 2nd, 2025
|
| 23 |
+
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
| 24 |
+
|
| 25 |
+
**Supported Languages:**
|
| 26 |
+
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.
|
| 27 |
+
|
| 28 |
+
**Intended use:**
|
| 29 |
+
The model is designed to respond to general instructions and can be used to build AI assistants for multiple domains, including business applications.
|
| 30 |
+
|
| 31 |
+
*Capabilities*
|
| 32 |
+
* Summarization
|
| 33 |
+
* Text classification
|
| 34 |
+
* Text extraction
|
| 35 |
+
* Question-answering
|
| 36 |
+
* Retrieval Augmented Generation (RAG)
|
| 37 |
+
* Code related tasks
|
| 38 |
+
* Function-calling tasks
|
| 39 |
+
* Multilingual dialog use cases
|
| 40 |
+
* Fill-In-the-Middle (FIM) code completions
|
| 41 |
+
|
| 42 |
+
<!-- <todo>Need to test the examples. (especially the tool calling and RAG ones)</todo>
|
| 43 |
+
-->
|
| 44 |
+
|
| 45 |
+
**Generation:**
|
| 46 |
+
This is a simple example of how to use Granite-4.0-H-Tiny model.
|
| 47 |
+
|
| 48 |
+
Install the following libraries:
|
| 49 |
+
|
| 50 |
+
```shell
|
| 51 |
+
pip install torch torchvision torchaudio
|
| 52 |
+
pip install accelerate
|
| 53 |
+
pip install transformers
|
| 54 |
+
```
|
| 55 |
+
Then, copy the snippet from the section that is relevant for your use case.
|
| 56 |
+
|
| 57 |
+
```python
|
| 58 |
+
import torch
|
| 59 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 60 |
+
|
| 61 |
+
device = "cuda"
|
| 62 |
+
model_path = "ibm-granite/granite-4.0-h-tiny"
|
| 63 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 64 |
+
# drop device_map if running on CPU
|
| 65 |
+
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
|
| 66 |
+
model.eval()
|
| 67 |
+
# change input text as desired
|
| 68 |
+
chat = [
|
| 69 |
+
{ "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
|
| 70 |
+
]
|
| 71 |
+
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
|
| 72 |
+
# tokenize the text
|
| 73 |
+
input_tokens = tokenizer(chat, return_tensors="pt").to(device)
|
| 74 |
+
# generate output tokens
|
| 75 |
+
output = model.generate(**input_tokens,
|
| 76 |
+
max_new_tokens=100)
|
| 77 |
+
# decode output tokens into text
|
| 78 |
+
output = tokenizer.batch_decode(output)
|
| 79 |
+
# print output
|
| 80 |
+
print(output[0])
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
Expected output:
|
| 84 |
+
```shell
|
| 85 |
+
<|start_of_role|>system<|end_of_role|>You are a helpful assistant. Please ensure responses are professional, accurate, and safe.<|end_of_text|>
|
| 86 |
+
<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|>
|
| 87 |
+
<|start_of_role|>assistant<|end_of_role|>Almaden Research Center, San Jose, California<|end_of_text|>
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
**Tool-calling:**
|
| 91 |
+
Granite-4.0-H-Tiny comes with enhanced tool calling capabilities, enabling seamless integration with external functions and APIs. To define a list of tools please follow OpenAI's function [definition schema](https://platform.openai.com/docs/guides/function-calling?api-mode=responses#defining-functions).
|
| 92 |
+
|
| 93 |
+
This is an example of how to use Granite-4.0-H-Tiny model tool-calling ability:
|
| 94 |
+
|
| 95 |
+
```python
|
| 96 |
+
tools = [
|
| 97 |
+
{
|
| 98 |
+
"type": "function",
|
| 99 |
+
"function": {
|
| 100 |
+
"name": "get_current_weather",
|
| 101 |
+
"description": "Get the current weather for a specified city.",
|
| 102 |
+
"parameters": {
|
| 103 |
+
"type": "object",
|
| 104 |
+
"properties": {
|
| 105 |
+
"city": {
|
| 106 |
+
"type": "string",
|
| 107 |
+
"description": "Name of the city"
|
| 108 |
+
}
|
| 109 |
+
},
|
| 110 |
+
"required": ["city"]
|
| 111 |
+
}
|
| 112 |
+
}
|
| 113 |
+
}
|
| 114 |
+
]
|
| 115 |
+
|
| 116 |
+
# change input text as desired
|
| 117 |
+
chat = [
|
| 118 |
+
{ "role": "user", "content": "What's the weather like in Boston right now?" },
|
| 119 |
+
]
|
| 120 |
+
chat = tokenizer.apply_chat_template(chat, \
|
| 121 |
+
tokenize=False, \
|
| 122 |
+
tools=tools, \
|
| 123 |
+
add_generation_prompt=True)
|
| 124 |
+
# tokenize the text
|
| 125 |
+
input_tokens = tokenizer(chat, return_tensors="pt").to(device)
|
| 126 |
+
# generate output tokens
|
| 127 |
+
output = model.generate(**input_tokens,
|
| 128 |
+
max_new_tokens=100)
|
| 129 |
+
# decode output tokens into text
|
| 130 |
+
output = tokenizer.batch_decode(output)
|
| 131 |
+
# print output
|
| 132 |
+
print(output[0])
|
| 133 |
+
```
|
| 134 |
+
|
| 135 |
+
Expected output:
|
| 136 |
+
```shell
|
| 137 |
+
<|start_of_role|>system<|end_of_role|>You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.
|
| 138 |
+
|
| 139 |
+
You are provided with function signatures within <tools></tools> XML tags:
|
| 140 |
+
<tools>
|
| 141 |
+
{"type": "function", "function": {"name": "get_current_weather", "description": "Get the current weather for a specified city.", "parameters": {"type": "object", "properties": {"city": {"type": "string", "description": "Name of the city"}}, "required": ["city"]}}}
|
| 142 |
+
</tools>
|
| 143 |
+
|
| 144 |
+
For each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
| 145 |
+
<tool_call>
|
| 146 |
+
{"name": <function-name>, "arguments": <args-json-object>}
|
| 147 |
+
</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.<|end_of_text|>
|
| 148 |
+
<|start_of_role|>user<|end_of_role|>What's the weather like in Boston right now?<|end_of_text|>
|
| 149 |
+
<|start_of_role|>assistant<|end_of_role|><tool_call>
|
| 150 |
+
{"name": "get_current_weather", "arguments": {"city": "Boston"}}
|
| 151 |
+
</tool_call><|end_of_text|>
|
| 152 |
+
```
|
| 153 |
+
|
| 154 |
+
<!-- **Retrieval Augmented Generation:**
|
| 155 |
+
*Coming soon* -->
|
| 156 |
+
|
| 157 |
+
**Evaluation Results:**
|
| 158 |
+
|
| 159 |
+
<table>
|
| 160 |
+
<!-- <caption><b> All Results</b></caption> -->
|
| 161 |
+
<thead>
|
| 162 |
+
<tr>
|
| 163 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
|
| 164 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Metric</th>
|
| 165 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
|
| 166 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
|
| 167 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
|
| 168 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
|
| 169 |
+
</tr>
|
| 170 |
+
</thead>
|
| 171 |
+
<tbody>
|
| 172 |
+
<tr>
|
| 173 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 174 |
+
General Tasks
|
| 175 |
+
</td>
|
| 176 |
+
</tr>
|
| 177 |
+
<tr>
|
| 178 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU</td>
|
| 179 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 180 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">65.98</td>
|
| 181 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.43</td>
|
| 182 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.65</td>
|
| 183 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">78.44</td>
|
| 184 |
+
</tr>
|
| 185 |
+
<tr>
|
| 186 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU-Pro</td>
|
| 187 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot, CoT</td>
|
| 188 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">44.5</td>
|
| 189 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">43.48</td>
|
| 190 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">44.94</td>
|
| 191 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">55.47</td>
|
| 192 |
+
</tr>
|
| 193 |
+
<tr>
|
| 194 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BBH</td>
|
| 195 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot, CoT</td>
|
| 196 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">72.48</td>
|
| 197 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">69.36</td>
|
| 198 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">66.34</td>
|
| 199 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.62</td>
|
| 200 |
+
</tr>
|
| 201 |
+
<tr>
|
| 202 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AGI EVAL</td>
|
| 203 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
|
| 204 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.29</td>
|
| 205 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">59</td>
|
| 206 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">62.15</td>
|
| 207 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.63</td>
|
| 208 |
+
</tr>
|
| 209 |
+
<tr>
|
| 210 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GPQA</td>
|
| 211 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
|
| 212 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">30.14</td>
|
| 213 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">32.15</td>
|
| 214 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">32.59</td>
|
| 215 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">40.63</td>
|
| 216 |
+
</tr>
|
| 217 |
+
<tr>
|
| 218 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 219 |
+
Alignment Tasks
|
| 220 |
+
</td>
|
| 221 |
+
</tr>
|
| 222 |
+
<tr>
|
| 223 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AlpacaEval 2.0</td>
|
| 224 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;"></td>
|
| 225 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">29.49</td>
|
| 226 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">31.49</td>
|
| 227 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">30.61</td>
|
| 228 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">42.48</td>
|
| 229 |
+
</tr>
|
| 230 |
+
<tr>
|
| 231 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">IFEval</td>
|
| 232 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Instruct, Strict</td>
|
| 233 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.5</td>
|
| 234 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">86.94</td>
|
| 235 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">84.78</td>
|
| 236 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">89.87</td>
|
| 237 |
+
</tr>
|
| 238 |
+
<tr>
|
| 239 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">IFEval</td>
|
| 240 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Prompt, Strict</td>
|
| 241 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">79.12</td>
|
| 242 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.71</td>
|
| 243 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">78.1</td>
|
| 244 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.22</td>
|
| 245 |
+
</tr>
|
| 246 |
+
<tr>
|
| 247 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">IFEval</td>
|
| 248 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Average</td>
|
| 249 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">82.31</td>
|
| 250 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">84.32</td>
|
| 251 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">81.44</td>
|
| 252 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">87.55</td>
|
| 253 |
+
</tr>
|
| 254 |
+
<tr>
|
| 255 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ArenaHard</td>
|
| 256 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
|
| 257 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">25.84</td>
|
| 258 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">36.15</td>
|
| 259 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">35.75</td>
|
| 260 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">46.48</td>
|
| 261 |
+
</tr>
|
| 262 |
+
<tr>
|
| 263 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 264 |
+
Math Tasks
|
| 265 |
+
</td>
|
| 266 |
+
</tr>
|
| 267 |
+
<tr>
|
| 268 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM8K</td>
|
| 269 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
|
| 270 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">85.45</td>
|
| 271 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.35</td>
|
| 272 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">84.69</td>
|
| 273 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">87.27</td>
|
| 274 |
+
</tr>
|
| 275 |
+
<tr>
|
| 276 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM8K Symbolic</td>
|
| 277 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
|
| 278 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">79.82</td>
|
| 279 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">77.5</td>
|
| 280 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">81.1</td>
|
| 281 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">87.38</td>
|
| 282 |
+
</tr>
|
| 283 |
+
<tr>
|
| 284 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Minerva Math</td>
|
| 285 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
|
| 286 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.06</td>
|
| 287 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.44</td>
|
| 288 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">69.64</td>
|
| 289 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">74</td>
|
| 290 |
+
</tr>
|
| 291 |
+
<tr>
|
| 292 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepMind Math</td>
|
| 293 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">0-shot, CoT</td>
|
| 294 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">44.56</td>
|
| 295 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">43.83</td>
|
| 296 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">49.92</td>
|
| 297 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">59.33</td>
|
| 298 |
+
</tr>
|
| 299 |
+
<tr>
|
| 300 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 301 |
+
Code Tasks
|
| 302 |
+
</td>
|
| 303 |
+
</tr>
|
| 304 |
+
<tr>
|
| 305 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval</td>
|
| 306 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 307 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">80</td>
|
| 308 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81</td>
|
| 309 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">83</td>
|
| 310 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">88</td>
|
| 311 |
+
</tr>
|
| 312 |
+
<tr>
|
| 313 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval+</td>
|
| 314 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 315 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">72</td>
|
| 316 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75</td>
|
| 317 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">76</td>
|
| 318 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83</td>
|
| 319 |
+
</tr>
|
| 320 |
+
<tr>
|
| 321 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP</td>
|
| 322 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 323 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">72</td>
|
| 324 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73</td>
|
| 325 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">80</td>
|
| 326 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">84</td>
|
| 327 |
+
</tr>
|
| 328 |
+
<tr>
|
| 329 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP+</td>
|
| 330 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 331 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64</td>
|
| 332 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64</td>
|
| 333 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">69</td>
|
| 334 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71</td>
|
| 335 |
+
</tr>
|
| 336 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">CRUXEval-O</td>
|
| 337 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 338 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">41.5</td>
|
| 339 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">41.25</td>
|
| 340 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">39.63</td>
|
| 341 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">50.25</td>
|
| 342 |
+
</tr>
|
| 343 |
+
<tr>
|
| 344 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BigCodeBench</td>
|
| 345 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 346 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">39.21</td>
|
| 347 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">37.9</td>
|
| 348 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">41.06</td>
|
| 349 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">46.23</td>
|
| 350 |
+
</tr>
|
| 351 |
+
<tr>
|
| 352 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 353 |
+
Tool Calling Tasks
|
| 354 |
+
</td>
|
| 355 |
+
</tr>
|
| 356 |
+
<tr>
|
| 357 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BFCL v3</td>
|
| 358 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
|
| 359 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">59.98</td>
|
| 360 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">57.56</td>
|
| 361 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">57.65</td>
|
| 362 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">64.69</td>
|
| 363 |
+
</tr>
|
| 364 |
+
<tr>
|
| 365 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 366 |
+
Multilingual Tasks
|
| 367 |
+
</td>
|
| 368 |
+
</tr>
|
| 369 |
+
<tr>
|
| 370 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MULTIPLE</td>
|
| 371 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
|
| 372 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">49.21</td>
|
| 373 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">49.46</td>
|
| 374 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">55.83</td>
|
| 375 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">57.37</td>
|
| 376 |
+
</tr>
|
| 377 |
+
<tr>
|
| 378 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
|
| 379 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 380 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">55.14</td>
|
| 381 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">55.19</td>
|
| 382 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">61.87</td>
|
| 383 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">69.69</td>
|
| 384 |
+
</tr>
|
| 385 |
+
<tr>
|
| 386 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
|
| 387 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
|
| 388 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">51.62</td>
|
| 389 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">50.51</td>
|
| 390 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">53.12</td>
|
| 391 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.97</td>
|
| 392 |
+
</tr>
|
| 393 |
+
<tr>
|
| 394 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
|
| 395 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
|
| 396 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">28.56</td>
|
| 397 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">44.48</td>
|
| 398 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">45.36</td>
|
| 399 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">38.72</td>
|
| 400 |
+
</tr>
|
| 401 |
+
<tr>
|
| 402 |
+
<td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
|
| 403 |
+
Safety
|
| 404 |
+
</td>
|
| 405 |
+
</tr>
|
| 406 |
+
<tr>
|
| 407 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">SALAD-Bench</td>
|
| 408 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
|
| 409 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">97.06</td>
|
| 410 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">96.28</td>
|
| 411 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">97.77</td>
|
| 412 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">97.3</td>
|
| 413 |
+
</tr>
|
| 414 |
+
<tr>
|
| 415 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AttaQ</td>
|
| 416 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;"></td>
|
| 417 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">86.05</td>
|
| 418 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">84.44</td>
|
| 419 |
+
<td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">86.61</td>
|
| 420 |
+
<td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">86.64</td>
|
| 421 |
+
</tr>
|
| 422 |
+
</tbody></table>
|
| 423 |
+
|
| 424 |
+
|
| 425 |
+
<table>
|
| 426 |
+
<caption><b>Multilingual Benchmarks and thr included languages:</b></caption>
|
| 427 |
+
<thead>
|
| 428 |
+
<tr>
|
| 429 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
|
| 430 |
+
<th style="text-align:left; background-color: #001d6c; color: white;"># Langs</th>
|
| 431 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Languages</th>
|
| 432 |
+
</tr>
|
| 433 |
+
</thead>
|
| 434 |
+
<tbody>
|
| 435 |
+
<tr>
|
| 436 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
|
| 437 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">11</td>
|
| 438 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ar, de, en, es, fr, ja, ko, pt, zh, bn, hi</td>
|
| 439 |
+
</tr>
|
| 440 |
+
<tr>
|
| 441 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
|
| 442 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">14</td>
|
| 443 |
+
<!-- <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> -->
|
| 444 |
+
<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>
|
| 445 |
+
|
| 446 |
+
</tr>
|
| 447 |
+
<tr>
|
| 448 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
|
| 449 |
+
<td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">5</td>
|
| 450 |
+
<td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">en, es, fr, ja, zh</td>
|
| 451 |
+
</tr>
|
| 452 |
+
</tbody>
|
| 453 |
+
</table>
|
| 454 |
+
|
| 455 |
+
**Model Architecture:**
|
| 456 |
+
Granite-4.0-H-Tiny baseline is built on a decoder-only MoE transformer architecture. Core components of this architecture are: GQA, Mamba2, MoEs with shared experts, SwiGLU activation, RMSNorm, and shared input/output embeddings.
|
| 457 |
+
|
| 458 |
+
<table>
|
| 459 |
+
<thead>
|
| 460 |
+
<tr>
|
| 461 |
+
<th style="text-align:left; background-color: #001d6c; color: white;">Model</th>
|
| 462 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
|
| 463 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
|
| 464 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
|
| 465 |
+
<th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
|
| 466 |
+
</tr></thead>
|
| 467 |
+
<tbody>
|
| 468 |
+
<tr>
|
| 469 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Embedding size</td>
|
| 470 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2560</td>
|
| 471 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">2048</td>
|
| 472 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">1536</td>
|
| 473 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4096</td>
|
| 474 |
+
</tr>
|
| 475 |
+
<tr>
|
| 476 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of layers</td>
|
| 477 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">40 attention</td>
|
| 478 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
|
| 479 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">4 attention / 36 Mamba2</td>
|
| 480 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
|
| 481 |
+
</tr>
|
| 482 |
+
<tr>
|
| 483 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Attention head size</td>
|
| 484 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 485 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 486 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">128</td>
|
| 487 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 488 |
+
</tr>
|
| 489 |
+
<tr>
|
| 490 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of attention heads</td>
|
| 491 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">40</td>
|
| 492 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
|
| 493 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">12</td>
|
| 494 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
|
| 495 |
+
</tr>
|
| 496 |
+
<tr>
|
| 497 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of KV heads</td>
|
| 498 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
|
| 499 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
|
| 500 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">4</td>
|
| 501 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
|
| 502 |
+
</tr>
|
| 503 |
+
<tr>
|
| 504 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Mamba2 state size</td>
|
| 505 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 506 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 507 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">128</td>
|
| 508 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 509 |
+
</tr>
|
| 510 |
+
<tr>
|
| 511 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Number of Mamba2 heads</td>
|
| 512 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 513 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
|
| 514 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">48</td>
|
| 515 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
|
| 516 |
+
</tr>
|
| 517 |
+
|
| 518 |
+
<tr>
|
| 519 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">MLP / Shared expert hidden size</td>
|
| 520 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
|
| 521 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
|
| 522 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">1024</td>
|
| 523 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">1536</td>
|
| 524 |
+
</tr>
|
| 525 |
+
|
| 526 |
+
|
| 527 |
+
<tr>
|
| 528 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Num. Experts</td>
|
| 529 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 530 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 531 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">64</td>
|
| 532 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">72</td>
|
| 533 |
+
</tr>
|
| 534 |
+
<tr>
|
| 535 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Num. active Experts</td>
|
| 536 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 537 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 538 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">6</td>
|
| 539 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
|
| 540 |
+
</tr>
|
| 541 |
+
<tr>
|
| 542 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Expert hidden size</td>
|
| 543 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 544 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
|
| 545 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">512</td>
|
| 546 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">768</td>
|
| 547 |
+
</tr>
|
| 548 |
+
|
| 549 |
+
<tr>
|
| 550 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">MLP activation</td>
|
| 551 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 552 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 553 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">SwiGLU</td>
|
| 554 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
|
| 555 |
+
</tr>
|
| 556 |
+
|
| 557 |
+
<tr>
|
| 558 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Sequence length</td>
|
| 559 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 560 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 561 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">128K</td>
|
| 562 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
|
| 563 |
+
</tr>
|
| 564 |
+
<tr>
|
| 565 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;">Position embedding</td>
|
| 566 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">RoPE</td>
|
| 567 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
|
| 568 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">NoPE</td>
|
| 569 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
|
| 570 |
+
</tr>
|
| 571 |
+
<tr>
|
| 572 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;"># Parameters</td>
|
| 573 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 574 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 575 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">7B</td>
|
| 576 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">32B</td>
|
| 577 |
+
</tr>
|
| 578 |
+
<tr>
|
| 579 |
+
<td style="text-align:left; background-color: #FFFFFF; color: black;"># Active parameters</td>
|
| 580 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 581 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
|
| 582 |
+
<td style="text-align:center; background-color: #DAE8FF; color: black;">1B</td>
|
| 583 |
+
<td style="text-align:center; background-color: #FFFFFF; color: black;">9B</td>
|
| 584 |
+
</tr>
|
| 585 |
+
</tbody></table>
|
| 586 |
+
|
| 587 |
+
**Training Data:**
|
| 588 |
+
Overall, our SFT data is largely comprised of three key sources: (1) publicly available datasets with permissive license, (2) internal synthetic data targeting specific capabilities, and (3) a select set of human-curated data.
|
| 589 |
+
|
| 590 |
+
**Infrastructure:**
|
| 591 |
+
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.
|
| 592 |
+
|
| 593 |
+
**Ethical Considerations and Limitations:**
|
| 594 |
+
Granite 4.0 Instruction Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering multiple languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks.
|
| 595 |
+
|
| 596 |
+
**Resources**
|
| 597 |
+
- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
|
| 598 |
+
- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
|
| 599 |
+
- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
|
| 600 |
+
|
| 601 |
+
<!-- ## Citation
|
| 602 |
+
```
|
| 603 |
+
@misc{granite-models,
|
| 604 |
+
author = {author 1, author2, ...},
|
| 605 |
+
title = {},
|
| 606 |
+
journal = {},
|
| 607 |
+
volume = {},
|
| 608 |
+
year = {2024},
|
| 609 |
+
url = {https://arxiv.org/abs/0000.00000},
|
| 610 |
+
}
|
| 611 |
+
``` -->
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
|
| 2 |
+
{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
|
| 3 |
+
{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
|
| 4 |
+
{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
|
| 5 |
+
{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
|
| 6 |
+
{%- if available_tools is defined and available_tools %}
|
| 7 |
+
{%- set tools = available_tools %}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
|
| 10 |
+
documents_system_message=documents_system_message_prefix,
|
| 11 |
+
default_system_message=g4_default_system_message,
|
| 12 |
+
system_message=''
|
| 13 |
+
) %}
|
| 14 |
+
{%- if tools %}
|
| 15 |
+
{%- for tool in tools %}
|
| 16 |
+
{%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
|
| 17 |
+
{%- endfor %}
|
| 18 |
+
{%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{%- set ns.tools_system_message = '' %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- if documents %}
|
| 23 |
+
{%- for document in documents %}
|
| 24 |
+
{%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
|
| 25 |
+
{%- endfor %}
|
| 26 |
+
{%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
|
| 27 |
+
{%- else %}
|
| 28 |
+
{%- set ns.documents_system_message = '' %}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- if messages[0].role == 'system' %}
|
| 31 |
+
{%- if messages[0].content is string %}
|
| 32 |
+
{%- set ns.system_message = messages[0].content %}
|
| 33 |
+
{%- elif messages[0].content is iterable %}
|
| 34 |
+
{%- for entry in messages[0].content %}
|
| 35 |
+
{%- if entry.type== 'text' %}
|
| 36 |
+
{%- if ns.system_message != '' %}
|
| 37 |
+
{%- set ns.system_message = ns.system_message + '\n' %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- set ns.system_message = ns.system_message + entry.text %}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if tools and documents %}
|
| 44 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
| 45 |
+
{%- elif tools %}
|
| 46 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
|
| 47 |
+
{%- elif documents %}
|
| 48 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- else %}
|
| 51 |
+
{%- if tools and documents %}
|
| 52 |
+
{%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
| 53 |
+
{%- elif tools %}
|
| 54 |
+
{%- set ns.system_message = ns.tools_system_message %}
|
| 55 |
+
{%- elif documents %}
|
| 56 |
+
{%- set ns.system_message = ns.documents_system_message %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- if ns.system_message %}
|
| 60 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{%- for message in messages %}
|
| 65 |
+
{%- set content = namespace(val='') %}
|
| 66 |
+
{%- if message.content is string %}
|
| 67 |
+
{%- set content.val = message.content %}
|
| 68 |
+
{%- else %}
|
| 69 |
+
{%- if message.content is iterable %}
|
| 70 |
+
{%- for entry in message.content %}
|
| 71 |
+
{%- if entry.type== 'text' %}
|
| 72 |
+
{%- if content.val != '' %}
|
| 73 |
+
{%- set content.val = content.val + '\n' %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- set content.val = content.val + entry.text %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endif %}
|
| 80 |
+
{%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
|
| 81 |
+
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
|
| 82 |
+
{%- elif message.role == 'assistant' %}
|
| 83 |
+
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
|
| 84 |
+
{%- if message.tool_calls %}
|
| 85 |
+
{%- for tool_call in message.tool_calls %}
|
| 86 |
+
{%- if (loop.first and content.val) or (not loop.first) %}
|
| 87 |
+
{{- '\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- if tool_call.function %}
|
| 90 |
+
{%- set tool_call = tool_call.function %}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 93 |
+
{{- tool_call.name }}
|
| 94 |
+
{{- '", "arguments": ' }}
|
| 95 |
+
{%- if tool_call.arguments is string %}
|
| 96 |
+
{{- tool_call.arguments }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{{- tool_call.arguments | tojson }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{{- '}\n</tool_call>' }}
|
| 101 |
+
{%- endfor %}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '<|end_of_text|>\n' }}
|
| 104 |
+
{%- elif message.role == 'tool' %}
|
| 105 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
|
| 106 |
+
{{- '<|start_of_role|>user<|end_of_role|>' }}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{{- '\n<tool_response>\n' }}
|
| 109 |
+
{{- content.val }}
|
| 110 |
+
{{- '\n</tool_response>' }}
|
| 111 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
|
| 112 |
+
{{- '<|end_of_text|>\n' }}
|
| 113 |
+
{%- endif %}
|
| 114 |
+
{%- endif %}
|
| 115 |
+
{%- endfor %}
|
| 116 |
+
{%- if add_generation_prompt %}
|
| 117 |
+
{{- '<|start_of_role|>assistant<|end_of_role|>' }}
|
| 118 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteMoeHybridForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"embedding_multiplier": 12,
|
| 10 |
+
"eos_token_id": 100257,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.1,
|
| 14 |
+
"intermediate_size": 512,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"mamba",
|
| 17 |
+
"mamba",
|
| 18 |
+
"mamba",
|
| 19 |
+
"mamba",
|
| 20 |
+
"mamba",
|
| 21 |
+
"attention",
|
| 22 |
+
"mamba",
|
| 23 |
+
"mamba",
|
| 24 |
+
"mamba",
|
| 25 |
+
"mamba",
|
| 26 |
+
"mamba",
|
| 27 |
+
"mamba",
|
| 28 |
+
"mamba",
|
| 29 |
+
"mamba",
|
| 30 |
+
"mamba",
|
| 31 |
+
"attention",
|
| 32 |
+
"mamba",
|
| 33 |
+
"mamba",
|
| 34 |
+
"mamba",
|
| 35 |
+
"mamba",
|
| 36 |
+
"mamba",
|
| 37 |
+
"mamba",
|
| 38 |
+
"mamba",
|
| 39 |
+
"mamba",
|
| 40 |
+
"mamba",
|
| 41 |
+
"attention",
|
| 42 |
+
"mamba",
|
| 43 |
+
"mamba",
|
| 44 |
+
"mamba",
|
| 45 |
+
"mamba",
|
| 46 |
+
"mamba",
|
| 47 |
+
"mamba",
|
| 48 |
+
"mamba",
|
| 49 |
+
"mamba",
|
| 50 |
+
"mamba",
|
| 51 |
+
"attention",
|
| 52 |
+
"mamba",
|
| 53 |
+
"mamba",
|
| 54 |
+
"mamba",
|
| 55 |
+
"mamba"
|
| 56 |
+
],
|
| 57 |
+
"logits_scaling": 6,
|
| 58 |
+
"mamba_chunk_size": 256,
|
| 59 |
+
"mamba_conv_bias": true,
|
| 60 |
+
"mamba_d_conv": 4,
|
| 61 |
+
"mamba_d_head": 64,
|
| 62 |
+
"mamba_d_state": 128,
|
| 63 |
+
"mamba_expand": 2,
|
| 64 |
+
"mamba_n_groups": 1,
|
| 65 |
+
"mamba_n_heads": 48,
|
| 66 |
+
"mamba_proj_bias": false,
|
| 67 |
+
"max_position_embeddings": 131072,
|
| 68 |
+
"model_type": "granitemoehybrid",
|
| 69 |
+
"normalization_function": "rmsnorm",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_experts_per_tok": 6,
|
| 72 |
+
"num_hidden_layers": 40,
|
| 73 |
+
"num_key_value_heads": 4,
|
| 74 |
+
"num_local_experts": 64,
|
| 75 |
+
"output_router_logits": false,
|
| 76 |
+
"pad_token_id": 100256,
|
| 77 |
+
"position_embedding_type": "nope",
|
| 78 |
+
"residual_multiplier": 0.22,
|
| 79 |
+
"rms_norm_eps": 1e-05,
|
| 80 |
+
"rope_scaling": null,
|
| 81 |
+
"rope_theta": 10000,
|
| 82 |
+
"router_aux_loss_coef": 0.0,
|
| 83 |
+
"shared_intermediate_size": 1024,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"torch_dtype": "bfloat16",
|
| 86 |
+
"transformers_version": "4.56.0",
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 100352
|
| 89 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"pad_token_id": 100256,
|
| 6 |
+
"transformers_version": "4.56.0"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d79109218e59c850b26146a40d5c2dd7084ac8e569e53a59e2dcb78a16529f73
|
| 3 |
+
size 4924822608
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f15b2625114d52bbe658050732687683a3596e14fab4a817d3147549ac609ef3
|
| 3 |
+
size 4879018632
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:825bf48c51808ce93042dc9ff65e6b8b76131fac76b8bda4183cff32abf39c83
|
| 3 |
+
size 4074301016
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 6939037248,
|
| 4 |
+
"total_size": 13878074496
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.mamba.D": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.mamba.D": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.1.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.1.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.mamba.D": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.10.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.10.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.10.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.10.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.10.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.10.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.10.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.11.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 58 |
+
"model.layers.11.mamba.D": "model-00001-of-00003.safetensors",
|
| 59 |
+
"model.layers.11.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 60 |
+
"model.layers.11.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"model.layers.11.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 62 |
+
"model.layers.11.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.11.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.11.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.11.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.11.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 71 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"model.layers.12.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 73 |
+
"model.layers.12.mamba.D": "model-00001-of-00003.safetensors",
|
| 74 |
+
"model.layers.12.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 75 |
+
"model.layers.12.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"model.layers.12.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 77 |
+
"model.layers.12.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"model.layers.12.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 79 |
+
"model.layers.12.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 80 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 81 |
+
"model.layers.12.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 82 |
+
"model.layers.12.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 83 |
+
"model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 84 |
+
"model.layers.13.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.13.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.13.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.13.mamba.D": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.13.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.13.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.13.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.13.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.13.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.13.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.13.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.14.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.14.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.14.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.14.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.14.mamba.D": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.14.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.14.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.14.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.14.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.14.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.14.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.14.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.14.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.15.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.15.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.15.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.15.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.15.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.16.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.16.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.16.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.16.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.16.mamba.D": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.16.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.16.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.16.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.16.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.16.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.16.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.16.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.16.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.17.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.17.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.17.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.17.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.17.mamba.D": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.17.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.17.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.17.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.17.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.17.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.17.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.17.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.17.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.18.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.18.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.18.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.18.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.18.mamba.D": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.18.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.18.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.layers.18.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.layers.18.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.layers.18.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.layers.18.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.18.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.18.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.19.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.19.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.19.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.19.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.19.mamba.D": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.19.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.19.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.19.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.19.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.19.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.19.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.19.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.19.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 185 |
+
"model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 186 |
+
"model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 187 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 188 |
+
"model.layers.2.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 189 |
+
"model.layers.2.mamba.D": "model-00001-of-00003.safetensors",
|
| 190 |
+
"model.layers.2.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 191 |
+
"model.layers.2.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 192 |
+
"model.layers.2.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 193 |
+
"model.layers.2.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 194 |
+
"model.layers.2.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 195 |
+
"model.layers.2.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 196 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 197 |
+
"model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 198 |
+
"model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 199 |
+
"model.layers.20.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.20.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.20.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.20.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.20.mamba.D": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.20.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.20.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.20.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.20.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.20.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.20.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.20.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.20.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.21.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.21.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.21.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.21.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.21.mamba.D": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.21.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.21.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.21.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.21.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.21.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.21.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.21.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.21.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.22.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.22.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.22.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.22.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.22.mamba.D": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.22.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.22.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.22.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.22.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.22.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.22.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.22.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.22.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.23.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.23.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.23.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.23.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.23.mamba.D": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.23.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.23.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.23.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.23.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.23.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.23.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.23.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.23.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.24.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.24.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.24.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 262 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"model.layers.24.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 264 |
+
"model.layers.24.mamba.D": "model-00002-of-00003.safetensors",
|
| 265 |
+
"model.layers.24.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.layers.24.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.24.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.24.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.24.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.24.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.24.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.24.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.layers.25.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 279 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 281 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.layers.25.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"model.layers.25.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.layers.26.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 287 |
+
"model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 288 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 289 |
+
"model.layers.26.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 290 |
+
"model.layers.26.mamba.D": "model-00002-of-00003.safetensors",
|
| 291 |
+
"model.layers.26.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 292 |
+
"model.layers.26.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 293 |
+
"model.layers.26.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 294 |
+
"model.layers.26.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 295 |
+
"model.layers.26.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 296 |
+
"model.layers.26.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 297 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 298 |
+
"model.layers.26.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 299 |
+
"model.layers.26.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 300 |
+
"model.layers.27.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 301 |
+
"model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 302 |
+
"model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
|
| 303 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 304 |
+
"model.layers.27.mamba.A_log": "model-00002-of-00003.safetensors",
|
| 305 |
+
"model.layers.27.mamba.D": "model-00002-of-00003.safetensors",
|
| 306 |
+
"model.layers.27.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 307 |
+
"model.layers.27.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"model.layers.27.mamba.dt_bias": "model-00002-of-00003.safetensors",
|
| 309 |
+
"model.layers.27.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"model.layers.27.mamba.norm.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"model.layers.27.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"model.layers.27.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
|
| 314 |
+
"model.layers.27.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.layers.28.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.28.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.28.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.28.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.28.mamba.D": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.28.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.28.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.28.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.28.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.28.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.28.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.28.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.28.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.29.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.29.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.29.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.29.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.29.mamba.D": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.29.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.29.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.29.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.29.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.29.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.29.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.29.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.29.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 346 |
+
"model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 347 |
+
"model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 348 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 349 |
+
"model.layers.3.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 350 |
+
"model.layers.3.mamba.D": "model-00001-of-00003.safetensors",
|
| 351 |
+
"model.layers.3.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 352 |
+
"model.layers.3.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 353 |
+
"model.layers.3.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 354 |
+
"model.layers.3.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 355 |
+
"model.layers.3.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 356 |
+
"model.layers.3.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 357 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 358 |
+
"model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 359 |
+
"model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 360 |
+
"model.layers.30.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.30.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.30.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.30.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.30.mamba.D": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.30.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.30.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.30.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.30.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.layers.30.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.layers.30.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.layers.30.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.layers.30.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.layers.31.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.layers.31.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.layers.31.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.layers.31.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.layers.31.mamba.D": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.layers.31.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.layers.31.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.layers.31.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.layers.31.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.layers.31.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.layers.31.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.layers.31.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.layers.31.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.layers.32.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.layers.32.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.layers.32.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.layers.32.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.layers.32.mamba.D": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.layers.32.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.layers.32.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.layers.32.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.layers.32.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.layers.32.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.layers.32.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.layers.32.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.layers.32.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.layers.33.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.layers.33.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.layers.33.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.layers.33.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.layers.33.mamba.D": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.layers.33.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.layers.33.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.layers.33.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.layers.33.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.layers.33.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.layers.33.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.layers.33.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.layers.33.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.layers.34.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.layers.34.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.layers.34.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.layers.34.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.layers.34.mamba.D": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.layers.34.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.layers.34.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.layers.34.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.layers.34.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.layers.34.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.layers.34.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.layers.34.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.layers.34.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.layers.35.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.layers.35.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.layers.35.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.layers.35.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.layers.35.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.layers.36.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.layers.36.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.layers.36.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.layers.36.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.layers.36.mamba.D": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.layers.36.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.layers.36.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.layers.36.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.layers.36.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.layers.36.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.layers.36.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 459 |
+
"model.layers.36.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 460 |
+
"model.layers.36.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 461 |
+
"model.layers.37.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 462 |
+
"model.layers.37.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 463 |
+
"model.layers.37.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 464 |
+
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 465 |
+
"model.layers.37.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 466 |
+
"model.layers.37.mamba.D": "model-00003-of-00003.safetensors",
|
| 467 |
+
"model.layers.37.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 468 |
+
"model.layers.37.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 469 |
+
"model.layers.37.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 470 |
+
"model.layers.37.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 471 |
+
"model.layers.37.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 472 |
+
"model.layers.37.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 473 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 474 |
+
"model.layers.37.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 475 |
+
"model.layers.37.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 476 |
+
"model.layers.38.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 477 |
+
"model.layers.38.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 478 |
+
"model.layers.38.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 479 |
+
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 480 |
+
"model.layers.38.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 481 |
+
"model.layers.38.mamba.D": "model-00003-of-00003.safetensors",
|
| 482 |
+
"model.layers.38.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 483 |
+
"model.layers.38.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 484 |
+
"model.layers.38.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 485 |
+
"model.layers.38.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 486 |
+
"model.layers.38.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 487 |
+
"model.layers.38.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 488 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 489 |
+
"model.layers.38.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 490 |
+
"model.layers.38.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 491 |
+
"model.layers.39.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 492 |
+
"model.layers.39.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 493 |
+
"model.layers.39.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
|
| 494 |
+
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 495 |
+
"model.layers.39.mamba.A_log": "model-00003-of-00003.safetensors",
|
| 496 |
+
"model.layers.39.mamba.D": "model-00003-of-00003.safetensors",
|
| 497 |
+
"model.layers.39.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 498 |
+
"model.layers.39.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 499 |
+
"model.layers.39.mamba.dt_bias": "model-00003-of-00003.safetensors",
|
| 500 |
+
"model.layers.39.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 501 |
+
"model.layers.39.mamba.norm.weight": "model-00003-of-00003.safetensors",
|
| 502 |
+
"model.layers.39.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 503 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 504 |
+
"model.layers.39.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
|
| 505 |
+
"model.layers.39.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
|
| 506 |
+
"model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 507 |
+
"model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 508 |
+
"model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 509 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 510 |
+
"model.layers.4.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 511 |
+
"model.layers.4.mamba.D": "model-00001-of-00003.safetensors",
|
| 512 |
+
"model.layers.4.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 513 |
+
"model.layers.4.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 514 |
+
"model.layers.4.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 515 |
+
"model.layers.4.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 516 |
+
"model.layers.4.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 517 |
+
"model.layers.4.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 518 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 519 |
+
"model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 520 |
+
"model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 521 |
+
"model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 522 |
+
"model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 523 |
+
"model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 524 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 525 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 526 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 527 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 528 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 529 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 530 |
+
"model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 531 |
+
"model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 532 |
+
"model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 533 |
+
"model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 534 |
+
"model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 535 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 536 |
+
"model.layers.6.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 537 |
+
"model.layers.6.mamba.D": "model-00001-of-00003.safetensors",
|
| 538 |
+
"model.layers.6.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 539 |
+
"model.layers.6.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 540 |
+
"model.layers.6.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 541 |
+
"model.layers.6.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 542 |
+
"model.layers.6.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 543 |
+
"model.layers.6.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 544 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 545 |
+
"model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 546 |
+
"model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 547 |
+
"model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 548 |
+
"model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 549 |
+
"model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 550 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 551 |
+
"model.layers.7.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 552 |
+
"model.layers.7.mamba.D": "model-00001-of-00003.safetensors",
|
| 553 |
+
"model.layers.7.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 554 |
+
"model.layers.7.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 555 |
+
"model.layers.7.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 556 |
+
"model.layers.7.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 557 |
+
"model.layers.7.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 558 |
+
"model.layers.7.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 559 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 560 |
+
"model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 561 |
+
"model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 562 |
+
"model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 563 |
+
"model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 564 |
+
"model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 565 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 566 |
+
"model.layers.8.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 567 |
+
"model.layers.8.mamba.D": "model-00001-of-00003.safetensors",
|
| 568 |
+
"model.layers.8.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 569 |
+
"model.layers.8.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 570 |
+
"model.layers.8.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 571 |
+
"model.layers.8.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 572 |
+
"model.layers.8.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 573 |
+
"model.layers.8.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 574 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 575 |
+
"model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 576 |
+
"model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 577 |
+
"model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 578 |
+
"model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 579 |
+
"model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
|
| 580 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 581 |
+
"model.layers.9.mamba.A_log": "model-00001-of-00003.safetensors",
|
| 582 |
+
"model.layers.9.mamba.D": "model-00001-of-00003.safetensors",
|
| 583 |
+
"model.layers.9.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 584 |
+
"model.layers.9.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 585 |
+
"model.layers.9.mamba.dt_bias": "model-00001-of-00003.safetensors",
|
| 586 |
+
"model.layers.9.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 587 |
+
"model.layers.9.mamba.norm.weight": "model-00001-of-00003.safetensors",
|
| 588 |
+
"model.layers.9.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 589 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 590 |
+
"model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
|
| 591 |
+
"model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
|
| 592 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 593 |
+
}
|
| 594 |
+
}
|
model.sig
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"mediaType":"application/vnd.dev.sigstore.bundle.v0.3+json","verificationMaterial":{"certificate":{"rawBytes":"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"},"tlogEntries":[{"logIndex":"663838764","logId":{"keyId":"wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="},"kindVersion":{"kind":"dsse","version":"0.0.1"},"integratedTime":"1762198595","inclusionPromise":{"signedEntryTimestamp":"MEUCIQCyBvH9KNQ5z7Ubm3Pi1lX+nq2bJP6JJAakLvJ/bIRWoAIgRyINeHGSqsnoLKCpCoQ+IVEaSk37a5jBc+BdlEkvMeE="},"inclusionProof":{"logIndex":"541934502","rootHash":"xFNgnT5vHtFNv4mS8IVsC5Vzkr5eIfMk39Z3UYauq+o=","treeSize":"541934516","hashes":["U4njLcsI5fXcndL0OchmVUW6bjMxR5cEEGweOsYTFzw=","IDCs8djk+yHs3Qz/ZGGNAphaqo8Ru2IQfZ/a+ECUwoI=","Pj0gwdqd7UCdR5s/1U0tLkZbhwbmG4LGr6F+11K/ExE=","rCegvoOvwuG0jtwFVtyp/QVhRvUOdxdnHBs7xfSabvo=","Fc+uu4Mb1WMsBrhRwjK0ZTS2SWm9m/l+U5KwU/vzaYc=","xz1k5gNuw2oo5YbCJiVD6TxGxIcaCKfkRCKkaqqZYGs=","WX9jk73qOSNSPo5mLNMTKY5jpAAlFIvjMIupj6BqmTI=","/uA6geAcbSWKWsTa8leKZiU0e6K7Z8KQazDgHWN+J7o=","x+HL/WN0KhLMnpMY9Ns38Ry0v4AA0tziv6QilwG9EsA=","dXlNLuJEwz5IfW+ZN0sLQ7dsXzhyj0Fa9rngJ+3e9TQ=","41/UOsoas7ueCE2PvijgQaw7zrwIfRPSpVQTdIUiUmU=","QLl5vwwLPxm6R6eJYkFWsegodbU08Lih3IlaHxNUxBM=","irnU1k46Z6LrXatUu5JH2Lgf0WSkmfdl35ZFLoOLYww=","G81uij9mV8vb1S+F2CjSBSznCSqLaz6WFdwrcU7blPo=","T4DqWD42hAtN+vX8jKCWqoC4meE4JekI9LxYGCcPy1M="],"checkpoint":{"envelope":"rekor.sigstore.dev - 1193050959916656506\n541934516\nxFNgnT5vHtFNv4mS8IVsC5Vzkr5eIfMk39Z3UYauq+o=\n\n— rekor.sigstore.dev wNI9ajBFAiEAwF9+u/Wh0dnt92q/EMgg1xAKxMDwtq72ECaZjnDj81YCIFHow7YXpH+XbdZ3LFj4gUNFu5AHYbluIj2ibPtwosMa\n"}},"canonicalizedBody":"eyJhcGlWZXJzaW9uIjoiMC4wLjEiLCJraW5kIjoiZHNzZSIsInNwZWMiOnsiZW52ZWxvcGVIYXNoIjp7ImFsZ29yaXRobSI6InNoYTI1NiIsInZhbHVlIjoiMTVlYTc0MjRjOTJjMDljMDRhYWVmYzZhNTVkMWIzMjEyZDE3Y2YzMDY1YjcwYmJjNWE1NmUyODJjZTlmN2VmOCJ9LCJwYXlsb2FkSGFzaCI6eyJhbGdvcml0aG0iOiJzaGEyNTYiLCJ2YWx1ZSI6IjFiOTYyZTc0MjNkMTBjY2U1MjhhNTFmZjg4YzEzZTQ0NDAwNjM0M2NlMTIxNzgxZTZmZWEwZWExODZhMmEyOTUifSwic2lnbmF0dXJlcyI6W3sic2lnbmF0dXJlIjoiTUVVQ0lDM0FRVWhCcGcva3lUVjFnQUxjaUh0M0Ivdzk0ZlRZbTRpRWh0WldXNlFLQWlFQXRYNTJLVW5xYTZKV1FzandlM1g5Z0hDR0tUbi9MdC83OW5LOEFUTWJ2Wk09IiwidmVyaWZpZXIiOiJMUzB0TFMxQ1JVZEpUaUJEUlZKVVNVWkpRMEZVUlMwdExTMHRDazFKU1VNMVZFTkRRVzExWjBGM1NVSkJaMGxWUmpKa1dWRnBRbTFRUlVZM2VYRlhTbnBaT1N0b1ltTTRSVzlCZDBObldVbExiMXBKZW1vd1JVRjNUWGNLVG5wRlZrMUNUVWRCTVZWRlEyaE5UV015Ykc1ak0xSjJZMjFWZFZwSFZqSk5ValIzU0VGWlJGWlJVVVJGZUZaNllWZGtlbVJIT1hsYVV6RndZbTVTYkFwamJURnNXa2RzYUdSSFZYZElhR05PVFdwVmVFMVVRWHBOVkd0NlRtcE5NVmRvWTA1TmFsVjRUVlJCZWsxVWF6Qk9hazB4VjJwQlFVMUdhM2RGZDFsSUNrdHZXa2w2YWpCRFFWRlpTVXR2V2tsNmFqQkVRVkZqUkZGblFVVktUWE5QVm14d1kySmhURUoxYVhOdVRqbE1lV2hCU0hSb1pFTXZMMmRGVEZGeE9IVUtWekZHTWk5emNTODNPSEZKY0Nzck5XNXZNQzl6UjBzdmVsZDVkVTl5UzI5alppOWhjVE5PUTJsQmVuSjVWa0pzVjB0UFEwRlpiM2RuWjBkSFRVRTBSd3BCTVZWa1JIZEZRaTkzVVVWQmQwbElaMFJCVkVKblRsWklVMVZGUkVSQlMwSm5aM0pDWjBWR1FsRmpSRUY2UVdSQ1owNVdTRkUwUlVablVWVnRWazFUQ2tOdFZIcHdVbTlRVVVOM1NURlljRko0Vm1KaVYwUTRkMGgzV1VSV1VqQnFRa0puZDBadlFWVXpPVkJ3ZWpGWmEwVmFZalZ4VG1wd1MwWlhhWGhwTkZrS1drUTRkMHBCV1VSV1VqQlNRVkZJTDBKQ2IzZEhTVVZYVWpOS2FHSnRiREJhVXpFeVdsaEtjRnB1YkVGaFYwcDBURzFPZG1KVVFUQkNaMjl5UW1kRlJRcEJXVTh2VFVGRlFrSkRXbTlrU0ZKM1kzcHZka3d6VG5CYU0wNHdZak5LYkV4dVdteGpiV3h0WlZNMWNGbHRNSFZaTWpsMFRESTVhR1JZVW05TmFrRXlDa0puYjNKQ1owVkZRVmxQTDAxQlJVbENRMmROU20xb01HUklRbnBQYVRoMll6SnNibU16VW5aamJWVjFaRzFXZVdGWFdqVk1iV3hwWWxNMWFtSXlNSFlLWWpKR01XUkhaM2xOU1VkTFFtZHZja0puUlVWQlpGbzFRV2RSUTBKSWQwVmxaMEkwUVVoWlFUTlVNSGRoYzJKSVJWUktha2RTTkdOdFYyTXpRWEZLU3dwWWNtcGxVRXN6TDJnMGNIbG5Remh3TjI4MFFVRkJSMkZUZW1sdGEyZEJRVUpCVFVGU2VrSkdRV2xDUlZGT1ZFcDNSV1ZoYUcweFdHTlFPR3BTTHpjNUNqQjFVMjVKY1ZSaFZuTTRSMGh3WTB4Q2JraHlTRkZKYUVGSmF6WnBPVzFyU1dsdWRGY3hNMDlOVkc5MlMwSmthRmxxVVd0SmNGQlVPRTAwVUV0bWRrSUtPVVphVlUxQmIwZERRM0ZIVTAwME9VSkJUVVJCTW1kQlRVZFZRMDFSUTIxMk5HZHhaalUxV21aSE5tbHFkV0pSU1ZkR2MwOWlkV28wVlhodFNsSjZNZ3BETTJ0V1pteFFOMjFFWXpoRlJWWmFZakJ0VHpVd1EzTTJiMXBTUXpoelEwMUZkbVZ3Y25ReGNXTXJlbTgwYjFFeU9DOTBNVFY0YnpobVFrcFFSVXN6Q2xwNVJURlFjR05OVG1Fdk4xVklkamxGTHpORVpuTlJZMUYyVWxaeFZHdzFWRkU5UFFvdExTMHRMVVZPUkNCRFJWSlVTVVpKUTBGVVJTMHRMUzB0Q2c9PSJ9XX19"}],"timestampVerificationData":{"rfc3161Timestamps":[{"signedTimestamp":"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"}]}},"dsseEnvelope":{"payload":"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","payloadType":"application/vnd.in-toto+json","signatures":[{"sig":"MEUCIC3AQUhBpg/kyTV1gALciHt3B/w94fTYm4iEhtZWW6QKAiEAtX52KUnqa6JWQsjwe3X9gHCGKTn/Lt/79nK8ATMbvZM="}]}}
|
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": 1000000000000000019884624838656,
|
| 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
|
|
|