Update README.md
Browse files
README.md
CHANGED
@@ -10,8 +10,6 @@ tags:
|
|
10 |
base_model:
|
11 |
- sthenno-com/miscii-14b-1225
|
12 |
- sthenno/tempesthenno-ppo-ckpt40
|
13 |
-
metrics:
|
14 |
-
- accuracy
|
15 |
model-index:
|
16 |
- name: miscii-14b-0218
|
17 |
results:
|
@@ -28,7 +26,8 @@ model-index:
|
|
28 |
value: 76.56
|
29 |
name: strict accuracy
|
30 |
source:
|
31 |
-
url:
|
|
|
32 |
name: Open LLM Leaderboard
|
33 |
- task:
|
34 |
type: text-generation
|
@@ -43,7 +42,8 @@ model-index:
|
|
43 |
value: 50.64
|
44 |
name: normalized accuracy
|
45 |
source:
|
46 |
-
url:
|
|
|
47 |
name: Open LLM Leaderboard
|
48 |
- task:
|
49 |
type: text-generation
|
@@ -58,7 +58,8 @@ model-index:
|
|
58 |
value: 51.44
|
59 |
name: exact match
|
60 |
source:
|
61 |
-
url:
|
|
|
62 |
name: Open LLM Leaderboard
|
63 |
- task:
|
64 |
type: text-generation
|
@@ -73,7 +74,8 @@ model-index:
|
|
73 |
value: 17.79
|
74 |
name: acc_norm
|
75 |
source:
|
76 |
-
url:
|
|
|
77 |
name: Open LLM Leaderboard
|
78 |
- task:
|
79 |
type: text-generation
|
@@ -88,7 +90,8 @@ model-index:
|
|
88 |
value: 13.21
|
89 |
name: acc_norm
|
90 |
source:
|
91 |
-
url:
|
|
|
92 |
name: Open LLM Leaderboard
|
93 |
- task:
|
94 |
type: text-generation
|
@@ -105,17 +108,23 @@ model-index:
|
|
105 |
value: 47.75
|
106 |
name: accuracy
|
107 |
source:
|
108 |
-
url:
|
|
|
109 |
name: Open LLM Leaderboard
|
110 |
---
|
111 |
# miscii-14b-0218
|
112 |
|
113 |
-
|
|
|
114 |
|
115 |
-
|
|
|
|
|
116 |
|
117 |
Image source: [The Angel’s Message](http://lastlabyrinth.net/agm/)
|
118 |
|
|
|
|
|
119 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
120 |
|
121 |
## Merge Details
|
@@ -156,16 +165,18 @@ models:
|
|
156 |
- model: /Users/sthenno/models/tempesthenno-sft-0218-stage2-ckpt60
|
157 |
|
158 |
```
|
159 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
160 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/sthenno-com__miscii-14b-0218-details)
|
161 |
-
|
162 |
-
| Metric |Value|
|
163 |
-
|-------------------|----:|
|
164 |
-
|Avg. |42.90|
|
165 |
-
|IFEval (0-Shot) |76.56|
|
166 |
-
|BBH (3-Shot) |50.64|
|
167 |
-
|MATH Lvl 5 (4-Shot)|51.44|
|
168 |
-
|GPQA (0-shot) |17.79|
|
169 |
-
|MuSR (0-shot) |13.21|
|
170 |
-
|MMLU-PRO (5-shot) |47.75|
|
171 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
base_model:
|
11 |
- sthenno-com/miscii-14b-1225
|
12 |
- sthenno/tempesthenno-ppo-ckpt40
|
|
|
|
|
13 |
model-index:
|
14 |
- name: miscii-14b-0218
|
15 |
results:
|
|
|
26 |
value: 76.56
|
27 |
name: strict accuracy
|
28 |
source:
|
29 |
+
url: >-
|
30 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
31 |
name: Open LLM Leaderboard
|
32 |
- task:
|
33 |
type: text-generation
|
|
|
42 |
value: 50.64
|
43 |
name: normalized accuracy
|
44 |
source:
|
45 |
+
url: >-
|
46 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
47 |
name: Open LLM Leaderboard
|
48 |
- task:
|
49 |
type: text-generation
|
|
|
58 |
value: 51.44
|
59 |
name: exact match
|
60 |
source:
|
61 |
+
url: >-
|
62 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
63 |
name: Open LLM Leaderboard
|
64 |
- task:
|
65 |
type: text-generation
|
|
|
74 |
value: 17.79
|
75 |
name: acc_norm
|
76 |
source:
|
77 |
+
url: >-
|
78 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
79 |
name: Open LLM Leaderboard
|
80 |
- task:
|
81 |
type: text-generation
|
|
|
90 |
value: 13.21
|
91 |
name: acc_norm
|
92 |
source:
|
93 |
+
url: >-
|
94 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
95 |
name: Open LLM Leaderboard
|
96 |
- task:
|
97 |
type: text-generation
|
|
|
108 |
value: 47.75
|
109 |
name: accuracy
|
110 |
source:
|
111 |
+
url: >-
|
112 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-0218
|
113 |
name: Open LLM Leaderboard
|
114 |
---
|
115 |
# miscii-14b-0218
|
116 |
|
117 |
+
$\text{I think there’s a reason I’m a shadow, but she looks like an angel.}$
|
118 |
+
> — *Viyella's Memory*, from *The Angel's Message* by Laur (2018).
|
119 |
|
120 |
+
<p align="center">
|
121 |
+
<img src="banner.png" alt="Banner" width="80%" style="border-radius:8px;">
|
122 |
+
</p>
|
123 |
|
124 |
Image source: [The Angel’s Message](http://lastlabyrinth.net/agm/)
|
125 |
|
126 |
+
-----
|
127 |
+
|
128 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
129 |
|
130 |
## Merge Details
|
|
|
165 |
- model: /Users/sthenno/models/tempesthenno-sft-0218-stage2-ckpt60
|
166 |
|
167 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
168 |
|
169 |
+
## Citation
|
170 |
+
|
171 |
+
Please use the following BibTeX entry to cite this model in your work:
|
172 |
+
|
173 |
+
```bibtex
|
174 |
+
@misc{sthenno-com_2025,
|
175 |
+
author = {{sthenno-com}},
|
176 |
+
title = {miscii-14b-0218 (Revision 92a6e4a)},
|
177 |
+
year = {2025},
|
178 |
+
url = {https://huggingface.co/sthenno-com/miscii-14b-0218},
|
179 |
+
doi = {10.57967/hf/4780},
|
180 |
+
publisher = {Hugging Face}
|
181 |
+
}
|
182 |
+
```
|