Commit
•
1ce79fa
1
Parent(s):
d6d5b63
Adding the Open Portuguese LLM Leaderboard Evaluation Results (#1)
Browse files- Adding the Open Portuguese LLM Leaderboard Evaluation Results (492ee6a602296202f027873f39a5952f6e4d7d8b)
Co-authored-by: Open PT LLM Leaderboard PR Bot <leaderboard-pt-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -11,6 +11,153 @@ tags:
|
|
11 |
base_model: unsloth/mistral-7b-bnb-4bit
|
12 |
datasets:
|
13 |
- lucianosb/cetacean-ptbr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
# Boto 7B v1.1
|
16 |
|
@@ -99,4 +246,23 @@ O uso do modelo é de inteira responsabilidade do usuário. O desenvolvedor do m
|
|
99 |
|
100 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
101 |
|
102 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
base_model: unsloth/mistral-7b-bnb-4bit
|
12 |
datasets:
|
13 |
- lucianosb/cetacean-ptbr
|
14 |
+
model-index:
|
15 |
+
- name: boto-7B-v1.1
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
type: text-generation
|
19 |
+
name: Text Generation
|
20 |
+
dataset:
|
21 |
+
name: ENEM Challenge (No Images)
|
22 |
+
type: eduagarcia/enem_challenge
|
23 |
+
split: train
|
24 |
+
args:
|
25 |
+
num_few_shot: 3
|
26 |
+
metrics:
|
27 |
+
- type: acc
|
28 |
+
value: 60.81
|
29 |
+
name: accuracy
|
30 |
+
source:
|
31 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
32 |
+
name: Open Portuguese LLM Leaderboard
|
33 |
+
- task:
|
34 |
+
type: text-generation
|
35 |
+
name: Text Generation
|
36 |
+
dataset:
|
37 |
+
name: BLUEX (No Images)
|
38 |
+
type: eduagarcia-temp/BLUEX_without_images
|
39 |
+
split: train
|
40 |
+
args:
|
41 |
+
num_few_shot: 3
|
42 |
+
metrics:
|
43 |
+
- type: acc
|
44 |
+
value: 49.37
|
45 |
+
name: accuracy
|
46 |
+
source:
|
47 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
48 |
+
name: Open Portuguese LLM Leaderboard
|
49 |
+
- task:
|
50 |
+
type: text-generation
|
51 |
+
name: Text Generation
|
52 |
+
dataset:
|
53 |
+
name: OAB Exams
|
54 |
+
type: eduagarcia/oab_exams
|
55 |
+
split: train
|
56 |
+
args:
|
57 |
+
num_few_shot: 3
|
58 |
+
metrics:
|
59 |
+
- type: acc
|
60 |
+
value: 42.28
|
61 |
+
name: accuracy
|
62 |
+
source:
|
63 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
64 |
+
name: Open Portuguese LLM Leaderboard
|
65 |
+
- task:
|
66 |
+
type: text-generation
|
67 |
+
name: Text Generation
|
68 |
+
dataset:
|
69 |
+
name: Assin2 RTE
|
70 |
+
type: assin2
|
71 |
+
split: test
|
72 |
+
args:
|
73 |
+
num_few_shot: 15
|
74 |
+
metrics:
|
75 |
+
- type: f1_macro
|
76 |
+
value: 88.12
|
77 |
+
name: f1-macro
|
78 |
+
source:
|
79 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
80 |
+
name: Open Portuguese LLM Leaderboard
|
81 |
+
- task:
|
82 |
+
type: text-generation
|
83 |
+
name: Text Generation
|
84 |
+
dataset:
|
85 |
+
name: Assin2 STS
|
86 |
+
type: eduagarcia/portuguese_benchmark
|
87 |
+
split: test
|
88 |
+
args:
|
89 |
+
num_few_shot: 15
|
90 |
+
metrics:
|
91 |
+
- type: pearson
|
92 |
+
value: 63.71
|
93 |
+
name: pearson
|
94 |
+
source:
|
95 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
96 |
+
name: Open Portuguese LLM Leaderboard
|
97 |
+
- task:
|
98 |
+
type: text-generation
|
99 |
+
name: Text Generation
|
100 |
+
dataset:
|
101 |
+
name: FaQuAD NLI
|
102 |
+
type: ruanchaves/faquad-nli
|
103 |
+
split: test
|
104 |
+
args:
|
105 |
+
num_few_shot: 15
|
106 |
+
metrics:
|
107 |
+
- type: f1_macro
|
108 |
+
value: 48.83
|
109 |
+
name: f1-macro
|
110 |
+
source:
|
111 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
112 |
+
name: Open Portuguese LLM Leaderboard
|
113 |
+
- task:
|
114 |
+
type: text-generation
|
115 |
+
name: Text Generation
|
116 |
+
dataset:
|
117 |
+
name: HateBR Binary
|
118 |
+
type: ruanchaves/hatebr
|
119 |
+
split: test
|
120 |
+
args:
|
121 |
+
num_few_shot: 25
|
122 |
+
metrics:
|
123 |
+
- type: f1_macro
|
124 |
+
value: 75.97
|
125 |
+
name: f1-macro
|
126 |
+
source:
|
127 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
128 |
+
name: Open Portuguese LLM Leaderboard
|
129 |
+
- task:
|
130 |
+
type: text-generation
|
131 |
+
name: Text Generation
|
132 |
+
dataset:
|
133 |
+
name: PT Hate Speech Binary
|
134 |
+
type: hate_speech_portuguese
|
135 |
+
split: test
|
136 |
+
args:
|
137 |
+
num_few_shot: 25
|
138 |
+
metrics:
|
139 |
+
- type: f1_macro
|
140 |
+
value: 64.66
|
141 |
+
name: f1-macro
|
142 |
+
source:
|
143 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
144 |
+
name: Open Portuguese LLM Leaderboard
|
145 |
+
- task:
|
146 |
+
type: text-generation
|
147 |
+
name: Text Generation
|
148 |
+
dataset:
|
149 |
+
name: tweetSentBR
|
150 |
+
type: eduagarcia/tweetsentbr_fewshot
|
151 |
+
split: test
|
152 |
+
args:
|
153 |
+
num_few_shot: 25
|
154 |
+
metrics:
|
155 |
+
- type: f1_macro
|
156 |
+
value: 55.45
|
157 |
+
name: f1-macro
|
158 |
+
source:
|
159 |
+
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=lucianosb/boto-7B-v1.1
|
160 |
+
name: Open Portuguese LLM Leaderboard
|
161 |
---
|
162 |
# Boto 7B v1.1
|
163 |
|
|
|
246 |
|
247 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
248 |
|
249 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
250 |
+
|
251 |
+
|
252 |
+
# Open Portuguese LLM Leaderboard Evaluation Results
|
253 |
+
|
254 |
+
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/lucianosb/boto-7B-v1.1) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
|
255 |
+
|
256 |
+
| Metric | Value |
|
257 |
+
|--------------------------|---------|
|
258 |
+
|Average |**61.02**|
|
259 |
+
|ENEM Challenge (No Images)| 60.81|
|
260 |
+
|BLUEX (No Images) | 49.37|
|
261 |
+
|OAB Exams | 42.28|
|
262 |
+
|Assin2 RTE | 88.12|
|
263 |
+
|Assin2 STS | 63.71|
|
264 |
+
|FaQuAD NLI | 48.83|
|
265 |
+
|HateBR Binary | 75.97|
|
266 |
+
|PT Hate Speech Binary | 64.66|
|
267 |
+
|tweetSentBR | 55.45|
|
268 |
+
|