Upload folder using huggingface_hub (#3)
Browse files- a878cb11a4e9e3c8623935bc4e712e0ce10f500c270a2d0f9def9d39e2ed76d6 (75e7023be4558c9932943571421c828b4b0859a7)
- fb6f0e041b485880af1a074ca46eee7dd70509e02a340a56bbc02edebbb1ee3a (b5b2123779e19e1ead2ed7527d7664d2db40c70a)
- e5c33a969e93463d93d2dd64605c59709377c3e93b8070b1c97556ef9bb405e0 (248f64648c24cf26549f6d03d87c894049e9ddb4)
- bf69fae5c77e9bb4d6401b71923e6387983946a34182bf4560dfcc8a504f8721 (634ac0a34b973df2edc99c9f0217c440bc0595c4)
- 752f403b98f3d67fdd21ac08123a7822e989e68a9acba078e0990dcc7481d2fe (f0cb91d3fc0e1038db0eacb42bc6d1ae1e04ad59)
- e82c66fda3e9b476807eaef7c9a598394afb83695e20bf56ce7383487537d50b (62bf0d7a8cfd82ba5842add92983ea0840dc91b1)
- 98065fa6ca8af8803e3f7373062904bcf178fa9e81b8ef2661cd514879dd03f2 (c3f88d83c5314e6fad1f09d1d9ade2aedf722faf)
- Delete .ipynb_checkpoints (9fb19be7b53964ed7094814427c6d6d1d7be96f3)
@@ -1,7 +1,6 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: other
|
5 |
tags:
|
6 |
- supernova
|
7 |
- moth
|
@@ -22,101 +21,7 @@ datasets:
|
|
22 |
- sequelbox/Supernova
|
23 |
pipeline_tag: text-generation
|
24 |
model_type: llama
|
25 |
-
|
26 |
-
- name: Llama3.1-8B-MOTH
|
27 |
-
results:
|
28 |
-
- task:
|
29 |
-
type: text-generation
|
30 |
-
name: Text Generation
|
31 |
-
dataset:
|
32 |
-
name: IFEval (0-Shot)
|
33 |
-
type: HuggingFaceH4/ifeval
|
34 |
-
args:
|
35 |
-
num_few_shot: 0
|
36 |
-
metrics:
|
37 |
-
- type: inst_level_strict_acc and prompt_level_strict_acc
|
38 |
-
value: 52.08
|
39 |
-
name: strict accuracy
|
40 |
-
source:
|
41 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
42 |
-
name: Open LLM Leaderboard
|
43 |
-
- task:
|
44 |
-
type: text-generation
|
45 |
-
name: Text Generation
|
46 |
-
dataset:
|
47 |
-
name: BBH (3-Shot)
|
48 |
-
type: BBH
|
49 |
-
args:
|
50 |
-
num_few_shot: 3
|
51 |
-
metrics:
|
52 |
-
- type: acc_norm
|
53 |
-
value: 26.45
|
54 |
-
name: normalized accuracy
|
55 |
-
source:
|
56 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
57 |
-
name: Open LLM Leaderboard
|
58 |
-
- task:
|
59 |
-
type: text-generation
|
60 |
-
name: Text Generation
|
61 |
-
dataset:
|
62 |
-
name: MATH Lvl 5 (4-Shot)
|
63 |
-
type: hendrycks/competition_math
|
64 |
-
args:
|
65 |
-
num_few_shot: 4
|
66 |
-
metrics:
|
67 |
-
- type: exact_match
|
68 |
-
value: 11.86
|
69 |
-
name: exact match
|
70 |
-
source:
|
71 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
72 |
-
name: Open LLM Leaderboard
|
73 |
-
- task:
|
74 |
-
type: text-generation
|
75 |
-
name: Text Generation
|
76 |
-
dataset:
|
77 |
-
name: GPQA (0-shot)
|
78 |
-
type: Idavidrein/gpqa
|
79 |
-
args:
|
80 |
-
num_few_shot: 0
|
81 |
-
metrics:
|
82 |
-
- type: acc_norm
|
83 |
-
value: 2.57
|
84 |
-
name: acc_norm
|
85 |
-
source:
|
86 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
87 |
-
name: Open LLM Leaderboard
|
88 |
-
- task:
|
89 |
-
type: text-generation
|
90 |
-
name: Text Generation
|
91 |
-
dataset:
|
92 |
-
name: MuSR (0-shot)
|
93 |
-
type: TAUR-Lab/MuSR
|
94 |
-
args:
|
95 |
-
num_few_shot: 0
|
96 |
-
metrics:
|
97 |
-
- type: acc_norm
|
98 |
-
value: 3.79
|
99 |
-
name: acc_norm
|
100 |
-
source:
|
101 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
102 |
-
name: Open LLM Leaderboard
|
103 |
-
- task:
|
104 |
-
type: text-generation
|
105 |
-
name: Text Generation
|
106 |
-
dataset:
|
107 |
-
name: MMLU-PRO (5-shot)
|
108 |
-
type: TIGER-Lab/MMLU-Pro
|
109 |
-
config: main
|
110 |
-
split: test
|
111 |
-
args:
|
112 |
-
num_few_shot: 5
|
113 |
-
metrics:
|
114 |
-
- type: acc
|
115 |
-
value: 25.48
|
116 |
-
name: accuracy
|
117 |
-
source:
|
118 |
-
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
|
119 |
-
name: Open LLM Leaderboard
|
120 |
---
|
121 |
|
122 |
- MOTH is a general chat AI.
|
@@ -126,20 +31,3 @@ model-index:
|
|
126 |
- MOTH is also available for [Gemma 2;](https://huggingface.co/sequelbox/gemma-2-9B-MOTH) more MOTH finetunes for other models to follow.
|
127 |
- MOTH has not been manually tested and uses automatically generated datasets.
|
128 |
- Do as you will.
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
(uses llama 3.1 license available at https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
|
133 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
134 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sequelbox__Llama3.1-8B-MOTH)
|
135 |
-
|
136 |
-
| Metric |Value|
|
137 |
-
|-------------------|----:|
|
138 |
-
|Avg. |20.37|
|
139 |
-
|IFEval (0-Shot) |52.08|
|
140 |
-
|BBH (3-Shot) |26.45|
|
141 |
-
|MATH Lvl 5 (4-Shot)|11.86|
|
142 |
-
|GPQA (0-shot) | 2.57|
|
143 |
-
|MuSR (0-shot) | 3.79|
|
144 |
-
|MMLU-PRO (5-shot) |25.48|
|
145 |
-
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
tags:
|
5 |
- supernova
|
6 |
- moth
|
|
|
21 |
- sequelbox/Supernova
|
22 |
pipeline_tag: text-generation
|
23 |
model_type: llama
|
24 |
+
license: llama3.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
---
|
26 |
|
27 |
- MOTH is a general chat AI.
|
|
|
31 |
- MOTH is also available for [Gemma 2;](https://huggingface.co/sequelbox/gemma-2-9B-MOTH) more MOTH finetunes for other models to follow.
|
32 |
- MOTH has not been manually tested and uses automatically generated datasets.
|
33 |
- Do as you will.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4886466168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c667b2d8329c90e1166715cc3df14b9360d9ddfb2adc03f3c09ee69855f43d
|
3 |
size 4886466168
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4832007448
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b0d0aee0981e7446e7b8a7b578d9df5fa94a9b06fc7d806dc39dae51ce89eaa
|
3 |
size 4832007448
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999813112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9ffbb084e9ba750dc51dc25514244fc43baf7b0231eaefdca6c2ece711ec25d
|
3 |
size 4999813112
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999813128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85182a7ae802d7d0145335b307978aac8e5e092c41eba7da95915d905a9ab1ea
|
3 |
size 4999813128
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4832007496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6280e315a2945db6f4079cb17cbb29fd2b49b654eed05e3b16aadeb3e4b4a094
|
3 |
size 4832007496
|
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999813120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8772867ea6533968a75a0f04a297b3abab768cc6b102ce4282ebd0b4580c897b
|
3 |
size 4999813120
|