whatmodel.sh / REBEL-Llama-3-Armo-iter_1
REBEL-Llama-3-Armo-iter_1
↗ share
+ contribute
REBEL-Llama-3-Armo-iter_1 is an open-weights language model from Cornell AGI (REBEL), released August 2024. Its published size is 8.03B parameters. Licence: apache-2.0.
Catalogue identity notes
Maker repo Cornell-AGI/REBEL-Llama-3-Armo-iter_1 @fac83cd: licence tag apache-2.0. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-08: month the maker's Hugging Face repo was created (createdAt 2024-08-28).
$ how it compares
The LLMs ranked either side of REBEL-Llama-3-Armo-iter_1, out of 1132 with a score, then more from Cornell AGI (REBEL).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 453 |  Mistral Small 3.1 24B (2503) | 54±1 | local | ||
| 454 |  Baichuan-M1-14B-Instruct | 54±4 | local | ||
| 455 | REBEL-Llama-3-Armo-iter_1 | 54±2 | local | ||
| 456 |  Apertus 70B Instruct (2509) | 54±6 | local | ||
| 457 |  Haha-7B | 54±6 | local | ||
| more from Cornell AGI (REBEL) | |||||
| 656 | REBEL-Llama-3 | 47±2 | local | ||
$ what it's good at
chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #233 of 466 * · 99% of its score · 1 test
Beats Granite 4.2 8B, Mistral Small 4 (119B-A6.5B), Olmo 3.1 32B Think here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Granite 4.0 H Micro 3B, Gemma 3n E4B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AlpacaEval 2 length-controlled | 49.3% ✎ | ▁▂▂▃▆▆█▆▄▄▁▁ beats 104/122 | 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-Armo-iter_1', 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 | = 54.0 |
$ 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