nicholasKluge
commited on
Commit
•
ae869ee
1
Parent(s):
c95afe2
Update README.md
Browse files
README.md
CHANGED
@@ -167,6 +167,8 @@ for i, completion in enumerate(completions):
|
|
167 |
|
168 |
## Benchmarks
|
169 |
|
|
|
|
|
170 |
| Models | Average | [ARC](https://arxiv.org/abs/1803.05457) | [Hellaswag](https://arxiv.org/abs/1905.07830) | [MMLU](https://arxiv.org/abs/2009.03300) | [TruthfulQA](https://arxiv.org/abs/2109.07958) |
|
171 |
|-------------------------------------------------------------------------------------|---------|-----------------------------------------|-----------------------------------------------|------------------------------------------|------------------------------------------------|
|
172 |
| [TeenyTinyLlama-460m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m) | 33.01 | 29.40 | 33.00 | 28.55 | 41.10 |
|
@@ -179,8 +181,6 @@ for i, completion in enumerate(completions):
|
|
179 |
| [Gpt2-small](https://huggingface.co/gpt2) | 29.97 | 21.48* | 31.60* | 25.79* | 40.65* |
|
180 |
| [Multilingual GPT](https://huggingface.co/ai-forever/mGPT) | 29.45 | 24.79 | 26.37* | 25.17* | 41.50 |
|
181 |
|
182 |
-
- Evaluations on benchmarks were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)). Thanks to [Laiviet](https://github.com/laiviet/lm-evaluation-harness) for translating some of the tasks in the LM-Evaluation-Harness. The results of models marked with an "*" were extracted from the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
|
183 |
-
|
184 |
## Fine-Tuning Comparisons
|
185 |
|
186 |
| Models | Average | [IMDB](https://huggingface.co/datasets/christykoh/imdb_pt) | [FaQuAD-NLI](https://huggingface.co/datasets/ruanchaves/faquad-nli) | [HateBr](https://huggingface.co/datasets/ruanchaves/hatebr) | [Assin2](https://huggingface.co/datasets/assin2) | [AgNews](https://huggingface.co/datasets/maritaca-ai/ag_news_pt) |
|
|
|
167 |
|
168 |
## Benchmarks
|
169 |
|
170 |
+
Evaluations on benchmarks were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)). Thanks to [Laiviet](https://github.com/laiviet/lm-evaluation-harness) for translating some of the tasks in the LM-Evaluation-Harness. The results of models marked with an "*" were extracted from the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
|
171 |
+
|
172 |
| Models | Average | [ARC](https://arxiv.org/abs/1803.05457) | [Hellaswag](https://arxiv.org/abs/1905.07830) | [MMLU](https://arxiv.org/abs/2009.03300) | [TruthfulQA](https://arxiv.org/abs/2109.07958) |
|
173 |
|-------------------------------------------------------------------------------------|---------|-----------------------------------------|-----------------------------------------------|------------------------------------------|------------------------------------------------|
|
174 |
| [TeenyTinyLlama-460m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-460m) | 33.01 | 29.40 | 33.00 | 28.55 | 41.10 |
|
|
|
181 |
| [Gpt2-small](https://huggingface.co/gpt2) | 29.97 | 21.48* | 31.60* | 25.79* | 40.65* |
|
182 |
| [Multilingual GPT](https://huggingface.co/ai-forever/mGPT) | 29.45 | 24.79 | 26.37* | 25.17* | 41.50 |
|
183 |
|
|
|
|
|
184 |
## Fine-Tuning Comparisons
|
185 |
|
186 |
| Models | Average | [IMDB](https://huggingface.co/datasets/christykoh/imdb_pt) | [FaQuAD-NLI](https://huggingface.co/datasets/ruanchaves/faquad-nli) | [HateBr](https://huggingface.co/datasets/ruanchaves/hatebr) | [Assin2](https://huggingface.co/datasets/assin2) | [AgNews](https://huggingface.co/datasets/maritaca-ai/ag_news_pt) |
|