Maggio33 commited on
Commit
0170c51
·
verified ·
1 Parent(s): 5f854a0

Slayer1B 1.09: update cards and training files

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -108,3 +108,21 @@ Weights are released under **Apache-2.0**, as 1.07; source corpora keep their ow
108
 
109
  A base language model can generate inaccurate, biased, offensive or personal information. Translated reasoning and technical text can contain errors; their presence does not demonstrate reasoning, technical reliability or instruction following. Privacy filtering is heuristic, and technical or tax material is not professional advice.
110
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
 
109
  A base language model can generate inaccurate, biased, offensive or personal information. Translated reasoning and technical text can contain errors; their presence does not demonstrate reasoning, technical reliability or instruction following. Privacy filtering is heuristic, and technical or tax material is not professional advice.
110
 
111
+
112
+ ## Acknowledgements
113
+
114
+ We thank the entire **BenchTeam / Fabryka AI** community for benchmark implementations, original-protocol documentation, evaluation runs and independent checks. The team is coordinated by **[@LoIlita](https://github.com/LoIlita) and [@Elwenor](https://github.com/Elwenor)**, as documented in the repository's [contribution guide](https://github.com/slayerlabs/benchmarks-fabryka-ai/blob/8b547007526971bd2fc35dfe56ff2c7d9b802568/CONTRIBUTING.md).
115
+
116
+ The following accounts contributed to [benchmarks-fabryka-ai](https://github.com/slayerlabs/benchmarks-fabryka-ai). This is a summary of documented contributions, not a ranking or a complete membership list.
117
+
118
+ | GitHub account | Documented contribution |
119
+ |---|---|
120
+ | [@LoIlita](https://github.com/LoIlita) | Team coordination and onboarding; evaluation workflow, methodology and benchmark reviews ([PR #92](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/92), [PR #185](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/185)). |
121
+ | [@Elwenor](https://github.com/Elwenor) | Team coordination; EWoK implementation, evaluation runner, multi-model benchmark run and reports ([PR #93](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/93), [PR #179](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/179)). |
122
+ | [@adgr3](https://github.com/adgr3) | Original-benchmark cards, numerical-verdict validation and dataset-licence review ([PR #94](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/94), [PR #144](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/144), [PR #175](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/175)). |
123
+ | [@gzawadzki](https://github.com/gzawadzki) | Slayer integration with lm-eval and WinoGrande evaluation ([PR #64](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/64), [PR #100](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/100)). |
124
+ | [@KateMajzel](https://github.com/KateMajzel) | MathQA and PubMedQA evaluation work ([PR #158](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/158), [PR #156](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/156)). |
125
+ | [@jakublvndsky](https://github.com/jakublvndsky) | HellaSwag reproduction and Slayer evaluation ([PR #149](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/149)). |
126
+ | [@janbanot](https://github.com/janbanot) | ARC-Easy original-benchmark card ([PR #70](https://github.com/slayerlabs/benchmarks-fabryka-ai/pull/70)). |
127
+
128
+ We invite BenchTeam, DatasetTeam and other contributors to propose **datasets for subsequent Slayer training runs**. The collaboration aims to assemble a DatasetTeam corpus of **one trillion (1T) tokens**. Source proposals should include provenance, version, language and domain coverage, applicable rights and known privacy or evaluation-overlap risks. This is a collection objective, not a claim that the corpus has already been assembled or used in Slayer1B 1.08.