Alignment-handbook Base model:cat-searcher/gemma-... Base model:finetune:cat-search... Dataset:cat-searcher/ultrafeed... Gemma2 Generated from trainer Region:us Safetensors Sharded Sppo Tensorboard Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/cat-searcher/gemma-2-9b-it-sppo-iter-1-evol-1
Gemma 2 9B It Sppo Iter 1 Evol 1 Benchmarks
MMLU Pro: 31.11
GPQA: 12.08
MUSR: 6.9
BBH: 41.1
IFEval: 29.42 vs 88 (so35)-66.6%
MATH Lvl 5: 8.53
LLME Score: 0.24285
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Gemma 2 9B It Sppo Iter 1 Evol 1 Parameters and Internals
| LLM Name | Gemma 2 9B It Sppo Iter 1 Evol 1 |
| Repository 🤗 | https://huggingface.co/cat-searcher/gemma-2-9b-it-sppo-iter-1-evol-1 |
| Base Model(s) | |
| Model Size | 9b |
| Required VRAM | 18.6 GB |
| Updated | 2024-09-23 |
| Maintainer | cat-searcher |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Gemma 2 9B It Sppo Iter 1 Evol 1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| G2 GSHT 32K | 32K / 20.4 GB | 9 | 1 |
| SystemGemma2 9B It | 32K / 18.6 GB | 22 | 2 |
| Gemma 2 9B It SimPO | 8K / 18.6 GB | 24338 | 166 |
| Gemma 2 9B It | 8K / 18.6 GB | 109842 | 719 |
| Gemma 2 9B | 8K / 37.1 GB | 101275 | 660 |
| Magnolia V3 Gemma2 8K 9B | 8K / 18.6 GB | 1750 | 3 |
| ...2 9B Cpt Sahabatai V1 Instruct | 8K / 18.6 GB | 3487 | 44 |
| Fanar 1 9B Instruct | 8K / 17.7 GB | 5629 | 22 |
| Darkest Muse V1 | 8K / 20.4 GB | 1769 | 81 |
| SILMA 9B Instruct V1.0 | 8K / 18.6 GB | 25623 | 75 |
Note: green Score (e.g. "73.2") means that the model is better than cat-searcher/gemma-2-9b-it-sppo-iter-1-evol-1 .
Rank the Gemma 2 9B It Sppo Iter 1 Evol 1 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 49452 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124