Update README.md
Browse files
README.md
CHANGED
@@ -5,8 +5,11 @@ language:
|
|
5 |
license: apache-2.0
|
6 |
library_name: transformers
|
7 |
tags:
|
|
|
|
|
8 |
- mergekit
|
9 |
- merge
|
|
|
10 |
base_model:
|
11 |
- sthenno-com/miscii-14b-1225
|
12 |
- sthenno/tempesthenno-ppo-ckpt40
|
@@ -114,40 +117,25 @@ model-index:
|
|
114 |
---
|
115 |
# miscii-14b-0218
|
116 |
|
117 |
-
|
|
|
118 |
|
119 |
-
<p align="
|
120 |
-
|
121 |
</p>
|
122 |
|
123 |
-
|
124 |
|
125 |
-
|
|
|
|
|
126 |
|
127 |
-
|
128 |
-
|
129 |
-
## Merge Details
|
130 |
-
### Merge Method
|
131 |
-
|
132 |
-
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /Users/sthenno/models/tempesthenno-ppo-enchanted as a base.
|
133 |
-
|
134 |
-
### Models Merged
|
135 |
-
|
136 |
-
The following models were included in the merge:
|
137 |
-
* /Users/sthenno/models/tempesthenno-sft-0218-stage2-ckpt40
|
138 |
-
* /Users/sthenno/models/tempesthenno-sft-0218-stage2-ckpt50
|
139 |
-
* /Users/sthenno/models/tempesthenno-sft-0218-stage2-ckpt60
|
140 |
-
* /Users/sthenno/models/tempesthenno-sft-0218-ckpt60
|
141 |
-
* /Users/sthenno/models/tempesthenno-sft-0218-ckpt80
|
142 |
-
|
143 |
-
### Configuration
|
144 |
-
|
145 |
-
The following YAML configuration was used to produce this model:
|
146 |
|
147 |
```yaml
|
148 |
-
name:
|
149 |
merge_method: model_stock
|
150 |
-
base_model:
|
151 |
tokenizer:
|
152 |
source: base
|
153 |
dtype: float32
|
@@ -157,17 +145,18 @@ parameters:
|
|
157 |
normalize: true
|
158 |
rescale: false
|
159 |
models:
|
160 |
-
- model:
|
161 |
-
- model:
|
162 |
-
- model:
|
163 |
-
- model:
|
164 |
-
- model:
|
165 |
-
|
166 |
```
|
167 |
|
168 |
## Citation
|
169 |
|
170 |
-
|
|
|
|
|
171 |
|
172 |
```bibtex
|
173 |
@misc{sthenno-com_2025,
|
@@ -178,4 +167,8 @@ Please use the following BibTeX entry to cite this model in your work:
|
|
178 |
doi = {10.57967/hf/4780},
|
179 |
publisher = {Hugging Face}
|
180 |
}
|
181 |
-
```
|
|
|
|
|
|
|
|
|
|
5 |
license: apache-2.0
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
+
- chat
|
9 |
+
- conversational
|
10 |
- mergekit
|
11 |
- merge
|
12 |
+
- miscii
|
13 |
base_model:
|
14 |
- sthenno-com/miscii-14b-1225
|
15 |
- sthenno/tempesthenno-ppo-ckpt40
|
|
|
117 |
---
|
118 |
# miscii-14b-0218
|
119 |
|
120 |
+
“I think there’s a reason I’m a shadow, but she looks like an angel.”
|
121 |
+
— **Viyella’s Memory**, excerpted from **[The Angel’s Message](http://lastlabyrinth.net/agm/)** by Laur (2018).
|
122 |
|
123 |
+
<p align="left">
|
124 |
+
<img src="banner@0.5x.png" alt="Banner" width="420" style="border-radius:3px;">
|
125 |
</p>
|
126 |
|
127 |
+
## Technical Specifications
|
128 |
|
129 |
+
**miscii-14b-0218** is a fine-tuned model based on **Qwen/Qwen2.5-14B-Instruct** ([Qwen Team, 2024](https://qwenlm.github.io/blog/qwen2.5/)).
|
130 |
+
It is developed using Arcee’s MergeKit ([Goddard et al. 2024](https://aclanthology.org/2024.emnlp-industry.36/)), employing the Model Stock merge method ([Jang, Yun, and Han 2024](https://arxiv.org/abs/2403.19522)).
|
131 |
+
The integration utilized **tempesthenno-ppo-enchanted** as the base model.
|
132 |
|
133 |
+
The configuration parameters for generating **miscii-14b-0218** are documented below:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
|
135 |
```yaml
|
136 |
+
name: miscii-14b-0218
|
137 |
merge_method: model_stock
|
138 |
+
base_model: tempesthenno-ppo-enchanted
|
139 |
tokenizer:
|
140 |
source: base
|
141 |
dtype: float32
|
|
|
145 |
normalize: true
|
146 |
rescale: false
|
147 |
models:
|
148 |
+
- model: tempesthenno-sft-0218-ckpt60
|
149 |
+
- model: tempesthenno-sft-0218-ckpt80
|
150 |
+
- model: tempesthenno-sft-0218-stage2-ckpt40
|
151 |
+
- model: tempesthenno-sft-0218-stage2-ckpt50
|
152 |
+
- model: tempesthenno-sft-0218-stage2-ckpt60
|
|
|
153 |
```
|
154 |
|
155 |
## Citation
|
156 |
|
157 |
+
If you find **miscii-14b-0218** useful for your research and applications, please use the following citation formats:
|
158 |
+
|
159 |
+
**BibTeX**
|
160 |
|
161 |
```bibtex
|
162 |
@misc{sthenno-com_2025,
|
|
|
167 |
doi = {10.57967/hf/4780},
|
168 |
publisher = {Hugging Face}
|
169 |
}
|
170 |
+
```
|
171 |
+
|
172 |
+
**Plain Text**
|
173 |
+
|
174 |
+
**Please cite as:** sthenno-com. miscii-14b-0218 (Revision 92a6e4a). Hugging Face, 2025. https://huggingface.co/sthenno-com/miscii-14b-0218.
|