whatmodel.sh / REBEL-Llama-3
REBEL-Llama-3
↗ share
+ contribute
REBEL-Llama-3 is an open-weights language model from Cornell AGI (REBEL), released May 2024. Licence: apache-2.0.
Catalogue identity notes
Maker repo Cornell-AGI/REBEL-Llama-3 @ce3a039: licence tag apache-2.0. Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-28).
$ how it compares
The LLMs ranked either side of REBEL-Llama-3, out of 1132 with a score, then more from Cornell AGI (REBEL).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 654 |  GLM-4 9B Chat | 47±2 | local | ||
| 655 |  Yi-1.5 34B (base) | 47±3 | local | ||
| 656 | REBEL-Llama-3 | 47±2 | local | ||
| 657 |  Infinity-Instruct-3M-0625-Mistral-7B | 47±2 | local | ||
| 658 | Infinity-Instruct-3M-0613-Llama3-70B | 47±2 | local | ||
| more from Cornell AGI (REBEL) | |||||
| 455 | REBEL-Llama-3-Armo-iter_1 | 54±2 | local | ||
$ what it's good at
chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #306 of 466 * · 99% of its score · 1 test
Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AlpacaEval 2 length-controlled | 31.4% ✎ | ▁▂▂▃▆▆█▆▄▄▁▁ beats 81/122 | 99% |
$ where to run it
Other ways to run it
- Run it as published · needs ~16.06 GB · from huggingface.co/Cornell-AGI (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Cornell-AGI/REBEL-Llama-3', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/Cornell-AGI ↗
$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 99%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository) | 1 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 47.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json