updated readme
Browse files
README.md
CHANGED
@@ -1,118 +1,118 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
pipeline_tag: text-generation
|
4 |
-
library_name: transformers
|
5 |
-
language: ['en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he', 'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my', 'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si', 'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn', 'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu']
|
6 |
-
datasets: [
|
7 |
-
'bigcode/programming-languages-keywords',
|
8 |
-
'bigcode/the-stack-smol-xs',
|
9 |
-
'nampdn-ai/tiny-textbooks',
|
10 |
-
'xu-song/cc100-samples',
|
11 |
-
'm-a-p/CodeFeedback-Filtered-Instruction',
|
12 |
-
'nampdn-ai/tiny-codes',
|
13 |
-
'ajibawa-2023/Maths-College',
|
14 |
-
'microsoft/orca-math-word-problems-200k',
|
15 |
-
'mlabonne/FineTome-100k',
|
16 |
-
'arcee-ai/agent-data',
|
17 |
-
'cognitivecomputations/SystemChat-2.0',
|
18 |
-
'badrex/llm-emoji-dataset',
|
19 |
-
]
|
20 |
-
tags:
|
21 |
-
- litgpt
|
22 |
-
- litdata
|
23 |
-
---
|
24 |
-
|
25 |
-
# tangled-llama-33m-32k-base-v0.1
|
26 |
-
|
27 |
-
<!--
|
28 |
-
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
29 |
-
|
30 |
-
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
31 |
-
|
32 |
-
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
33 |
-
|
34 |
-
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
35 |
-
-->
|
36 |
-
|
37 |
-
## lm-evaluation-harness
|
38 |
-
|
39 |
-
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
40 |
-
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
41 |
-
|arc_challenge | 1|none | 0|acc |↑ |0.2065|± |0.0118|
|
42 |
-
| | |none | 0|acc_norm |↑ |0.2338|± |0.0124|
|
43 |
-
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033|
|
44 |
-
| | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000|
|
45 |
-
|hellaswag | 1|none | 0|acc |↑ |0.2614|± |0.0044|
|
46 |
-
| | |none | 0|acc_norm |↑ |0.2604|± |0.0044|
|
47 |
-
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
48 |
-
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
49 |
-
| - formal_logic | 1|none | 0|acc |↑ |0.2698|± |0.0397|
|
50 |
-
| - high_school_european_history | 1|none | 0|acc |↑ |0.2000|± |0.0312|
|
51 |
-
| - high_school_us_history | 1|none | 0|acc |↑ |0.2500|± |0.0304|
|
52 |
-
| - high_school_world_history | 1|none | 0|acc |↑ |0.2785|± |0.0292|
|
53 |
-
| - international_law | 1|none | 0|acc |↑ |0.2149|± |0.0375|
|
54 |
-
| - jurisprudence | 1|none | 0|acc |↑ |0.2407|± |0.0413|
|
55 |
-
| - logical_fallacies | 1|none | 0|acc |↑ |0.2270|± |0.0329|
|
56 |
-
| - moral_disputes | 1|none | 0|acc |↑ |0.2341|± |0.0228|
|
57 |
-
| - moral_scenarios | 1|none | 0|acc |↑ |0.2380|± |0.0142|
|
58 |
-
| - philosophy | 1|none | 0|acc |↑ |0.1833|± |0.0220|
|
59 |
-
| - prehistory | 1|none | 0|acc |↑ |0.2160|± |0.0229|
|
60 |
-
| - professional_law | 1|none | 0|acc |↑ |0.2399|± |0.0109|
|
61 |
-
| - world_religions | 1|none | 0|acc |↑ |0.3275|± |0.0360|
|
62 |
-
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
63 |
-
| - business_ethics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
64 |
-
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258|
|
65 |
-
| - college_medicine | 1|none | 0|acc |↑ |0.2486|± |0.0330|
|
66 |
-
| - global_facts | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
67 |
-
| - human_aging | 1|none | 0|acc |↑ |0.3229|± |0.0314|
|
68 |
-
| - management | 1|none | 0|acc |↑ |0.1845|± |0.0384|
|
69 |
-
| - marketing | 1|none | 0|acc |↑ |0.3034|± |0.0301|
|
70 |
-
| - medical_genetics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
71 |
-
| - miscellaneous | 1|none | 0|acc |↑ |0.2401|± |0.0153|
|
72 |
-
| - nutrition | 1|none | 0|acc |↑ |0.2418|± |0.0245|
|
73 |
-
| - professional_accounting | 1|none | 0|acc |↑ |0.2411|± |0.0255|
|
74 |
-
| - professional_medicine | 1|none | 0|acc |↑ |0.1838|± |0.0235|
|
75 |
-
| - virology | 1|none | 0|acc |↑ |0.2831|± |0.0351|
|
76 |
-
| - social sciences | 2|none | |acc |↑ |0.2155|± |0.0074|
|
77 |
-
| - econometrics | 1|none | 0|acc |↑ |0.2281|± |0.0395|
|
78 |
-
| - high_school_geography | 1|none | 0|acc |↑ |0.1768|± |0.0272|
|
79 |
-
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.1969|± |0.0287|
|
80 |
-
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2103|± |0.0207|
|
81 |
-
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.2143|± |0.0267|
|
82 |
-
| - high_school_psychology | 1|none | 0|acc |↑ |0.1872|± |0.0167|
|
83 |
-
| - human_sexuality | 1|none | 0|acc |↑ |0.2672|± |0.0388|
|
84 |
-
| - professional_psychology | 1|none | 0|acc |↑ |0.2467|± |0.0174|
|
85 |
-
| - public_relations | 1|none | 0|acc |↑ |0.2182|± |0.0396|
|
86 |
-
| - security_studies | 1|none | 0|acc |↑ |0.1755|± |0.0244|
|
87 |
-
| - sociology | 1|none | 0|acc |↑ |0.2438|± |0.0304|
|
88 |
-
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
89 |
-
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|
90 |
-
| - abstract_algebra | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
91 |
-
| - anatomy | 1|none | 0|acc |↑ |0.1778|± |0.0330|
|
92 |
-
| - astronomy | 1|none | 0|acc |↑ |0.1776|± |0.0311|
|
93 |
-
| - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365|
|
94 |
-
| - college_chemistry | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
95 |
-
| - college_computer_science | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
96 |
-
| - college_mathematics | 1|none | 0|acc |↑ |0.2100|± |0.0409|
|
97 |
-
| - college_physics | 1|none | 0|acc |↑ |0.2059|± |0.0402|
|
98 |
-
| - computer_security | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
99 |
-
| - conceptual_physics | 1|none | 0|acc |↑ |0.2681|± |0.0290|
|
100 |
-
| - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353|
|
101 |
-
| - elementary_mathematics | 1|none | 0|acc |↑ |0.2011|± |0.0206|
|
102 |
-
| - high_school_biology | 1|none | 0|acc |↑ |0.1806|± |0.0219|
|
103 |
-
| - high_school_chemistry | 1|none | 0|acc |↑ |0.1478|± |0.0250|
|
104 |
-
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
105 |
-
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2111|± |0.0249|
|
106 |
-
| - high_school_physics | 1|none | 0|acc |↑ |0.1788|± |0.0313|
|
107 |
-
| - high_school_statistics | 1|none | 0|acc |↑ |0.1620|± |0.0251|
|
108 |
-
| - machine_learning | 1|none | 0|acc |↑ |0.2768|± |0.0425|
|
109 |
-
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4975|± |0.0165|
|
110 |
-
|winogrande | 1|none | 0|acc |↑ |0.5146|± |0.0140|
|
111 |
-
|
112 |
-
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
113 |
-
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
114 |
-
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
115 |
-
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
116 |
-
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
117 |
-
| - social sciences| 2|none | |acc |↑ |0.2155|± |0.0074|
|
118 |
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
library_name: transformers
|
5 |
+
language: ['en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he', 'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my', 'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si', 'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn', 'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu']
|
6 |
+
datasets: [
|
7 |
+
'bigcode/programming-languages-keywords',
|
8 |
+
'bigcode/the-stack-smol-xs',
|
9 |
+
'nampdn-ai/tiny-textbooks',
|
10 |
+
'xu-song/cc100-samples',
|
11 |
+
'm-a-p/CodeFeedback-Filtered-Instruction',
|
12 |
+
'nampdn-ai/tiny-codes',
|
13 |
+
'ajibawa-2023/Maths-College',
|
14 |
+
'microsoft/orca-math-word-problems-200k',
|
15 |
+
'mlabonne/FineTome-100k',
|
16 |
+
'arcee-ai/agent-data',
|
17 |
+
'cognitivecomputations/SystemChat-2.0',
|
18 |
+
'badrex/llm-emoji-dataset',
|
19 |
+
]
|
20 |
+
tags:
|
21 |
+
- litgpt
|
22 |
+
- litdata
|
23 |
+
---
|
24 |
+
|
25 |
+
# tangled-llama-33m-32k-base-v0.1
|
26 |
+
|
27 |
+
<!--
|
28 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
29 |
+
|
30 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
31 |
+
|
32 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
33 |
+
|
34 |
+
<iframe src="https://wandb.ai/mtasic85/pretrain-/runs/lr5thq6l?nw=nwusermtasic85" style="border:none;height:1024px;width:100%">
|
35 |
+
-->
|
36 |
+
|
37 |
+
## lm-evaluation-harness
|
38 |
+
|
39 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
40 |
+
|---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
41 |
+
|arc_challenge | 1|none | 0|acc |↑ |0.2065|± |0.0118|
|
42 |
+
| | |none | 0|acc_norm |↑ |0.2338|± |0.0124|
|
43 |
+
|gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033|
|
44 |
+
| | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000|
|
45 |
+
|hellaswag | 1|none | 0|acc |↑ |0.2614|± |0.0044|
|
46 |
+
| | |none | 0|acc_norm |↑ |0.2604|± |0.0044|
|
47 |
+
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
48 |
+
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
49 |
+
| - formal_logic | 1|none | 0|acc |↑ |0.2698|± |0.0397|
|
50 |
+
| - high_school_european_history | 1|none | 0|acc |↑ |0.2000|± |0.0312|
|
51 |
+
| - high_school_us_history | 1|none | 0|acc |↑ |0.2500|± |0.0304|
|
52 |
+
| - high_school_world_history | 1|none | 0|acc |↑ |0.2785|± |0.0292|
|
53 |
+
| - international_law | 1|none | 0|acc |↑ |0.2149|± |0.0375|
|
54 |
+
| - jurisprudence | 1|none | 0|acc |↑ |0.2407|± |0.0413|
|
55 |
+
| - logical_fallacies | 1|none | 0|acc |↑ |0.2270|± |0.0329|
|
56 |
+
| - moral_disputes | 1|none | 0|acc |↑ |0.2341|± |0.0228|
|
57 |
+
| - moral_scenarios | 1|none | 0|acc |↑ |0.2380|± |0.0142|
|
58 |
+
| - philosophy | 1|none | 0|acc |↑ |0.1833|± |0.0220|
|
59 |
+
| - prehistory | 1|none | 0|acc |↑ |0.2160|± |0.0229|
|
60 |
+
| - professional_law | 1|none | 0|acc |↑ |0.2399|± |0.0109|
|
61 |
+
| - world_religions | 1|none | 0|acc |↑ |0.3275|± |0.0360|
|
62 |
+
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
63 |
+
| - business_ethics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
64 |
+
| - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258|
|
65 |
+
| - college_medicine | 1|none | 0|acc |↑ |0.2486|± |0.0330|
|
66 |
+
| - global_facts | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
67 |
+
| - human_aging | 1|none | 0|acc |↑ |0.3229|± |0.0314|
|
68 |
+
| - management | 1|none | 0|acc |↑ |0.1845|± |0.0384|
|
69 |
+
| - marketing | 1|none | 0|acc |↑ |0.3034|± |0.0301|
|
70 |
+
| - medical_genetics | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|
71 |
+
| - miscellaneous | 1|none | 0|acc |↑ |0.2401|± |0.0153|
|
72 |
+
| - nutrition | 1|none | 0|acc |↑ |0.2418|± |0.0245|
|
73 |
+
| - professional_accounting | 1|none | 0|acc |↑ |0.2411|± |0.0255|
|
74 |
+
| - professional_medicine | 1|none | 0|acc |↑ |0.1838|± |0.0235|
|
75 |
+
| - virology | 1|none | 0|acc |↑ |0.2831|± |0.0351|
|
76 |
+
| - social sciences | 2|none | |acc |↑ |0.2155|± |0.0074|
|
77 |
+
| - econometrics | 1|none | 0|acc |↑ |0.2281|± |0.0395|
|
78 |
+
| - high_school_geography | 1|none | 0|acc |↑ |0.1768|± |0.0272|
|
79 |
+
| - high_school_government_and_politics| 1|none | 0|acc |↑ |0.1969|± |0.0287|
|
80 |
+
| - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2103|± |0.0207|
|
81 |
+
| - high_school_microeconomics | 1|none | 0|acc |↑ |0.2143|± |0.0267|
|
82 |
+
| - high_school_psychology | 1|none | 0|acc |↑ |0.1872|± |0.0167|
|
83 |
+
| - human_sexuality | 1|none | 0|acc |↑ |0.2672|± |0.0388|
|
84 |
+
| - professional_psychology | 1|none | 0|acc |↑ |0.2467|± |0.0174|
|
85 |
+
| - public_relations | 1|none | 0|acc |↑ |0.2182|± |0.0396|
|
86 |
+
| - security_studies | 1|none | 0|acc |↑ |0.1755|± |0.0244|
|
87 |
+
| - sociology | 1|none | 0|acc |↑ |0.2438|± |0.0304|
|
88 |
+
| - us_foreign_policy | 1|none | 0|acc |↑ |0.2700|± |0.0446|
|
89 |
+
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|
90 |
+
| - abstract_algebra | 1|none | 0|acc |↑ |0.1700|± |0.0378|
|
91 |
+
| - anatomy | 1|none | 0|acc |↑ |0.1778|± |0.0330|
|
92 |
+
| - astronomy | 1|none | 0|acc |↑ |0.1776|± |0.0311|
|
93 |
+
| - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365|
|
94 |
+
| - college_chemistry | 1|none | 0|acc |↑ |0.1900|± |0.0394|
|
95 |
+
| - college_computer_science | 1|none | 0|acc |↑ |0.2600|± |0.0441|
|
96 |
+
| - college_mathematics | 1|none | 0|acc |↑ |0.2100|± |0.0409|
|
97 |
+
| - college_physics | 1|none | 0|acc |↑ |0.2059|± |0.0402|
|
98 |
+
| - computer_security | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
99 |
+
| - conceptual_physics | 1|none | 0|acc |↑ |0.2681|± |0.0290|
|
100 |
+
| - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353|
|
101 |
+
| - elementary_mathematics | 1|none | 0|acc |↑ |0.2011|± |0.0206|
|
102 |
+
| - high_school_biology | 1|none | 0|acc |↑ |0.1806|± |0.0219|
|
103 |
+
| - high_school_chemistry | 1|none | 0|acc |↑ |0.1478|± |0.0250|
|
104 |
+
| - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429|
|
105 |
+
| - high_school_mathematics | 1|none | 0|acc |↑ |0.2111|± |0.0249|
|
106 |
+
| - high_school_physics | 1|none | 0|acc |↑ |0.1788|± |0.0313|
|
107 |
+
| - high_school_statistics | 1|none | 0|acc |↑ |0.1620|± |0.0251|
|
108 |
+
| - machine_learning | 1|none | 0|acc |↑ |0.2768|± |0.0425|
|
109 |
+
|truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4975|± |0.0165|
|
110 |
+
|winogrande | 1|none | 0|acc |↑ |0.5146|± |0.0140|
|
111 |
+
|
112 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
113 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
114 |
+
|mmlu | 2|none | |acc |↑ |0.2280|± |0.0035|
|
115 |
+
| - humanities | 2|none | |acc |↑ |0.2376|± |0.0062|
|
116 |
+
| - other | 2|none | |acc |↑ |0.2481|± |0.0077|
|
117 |
+
| - social sciences| 2|none | |acc |↑ |0.2155|± |0.0074|
|
118 |
| - stem | 2|none | |acc |↑ |0.2058|± |0.0072|
|