Arxiv:2503.08942 Autotrain compatible Base model:finetune:vectorzhou... Base model:vectorzhou/gemma-2-... Conversational Dataset:pku-alignment/pku-safe... Endpoints compatible Extra-gradient Finetuned Gemma2 Generated from trainer Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/vectorzhou/gemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-OnlineIPO1-0907045617-epoch-3
Gemma 2 2B It Alpaca Cleaned SFT PKU SafeRLHF OnlineIPO1 0907045617 Epoch 3 Benchmarks
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 2B It Alpaca Cleaned SFT PKU SafeRLHF OnlineIPO1 0907045617 Epoch 3 Parameters and Internals
| LLM Name | Gemma 2 2B It Alpaca Cleaned SFT PKU SafeRLHF OnlineIPO1 0907045617 Epoch 3 |
| Repository 🤗 | https://huggingface.co/vectorzhou/gemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-OnlineIPO1-0907045617-epoch-3 |
| Model Name | gemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-OnlineIPO1 |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 6.4 GB |
| Updated | 2025-09-22 |
| Maintainer | vectorzhou |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.48.0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Gemma 2 2B It Alpaca Cleaned SFT PKU SafeRLHF OnlineIPO1 0907045617 Epoch 3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SJT 2B | 128K / 5.2 GB | 5 | 0 |
| SILMA Kashif 2B Instruct V1.0 | 12K / 5.2 GB | 6746 | 18 |
| ...mma 2 2B Jpn It Finetuning Sft | 8K / 5.2 GB | 10 | 0 |
| Gemma 2 2B It | 8K / 5.2 GB | 421819 | 908 |
| Gemma 2 2B | 8K / 10.5 GB | 182986 | 487 |
| Gemma 2 2B Jpn It | 8K / 5.2 GB | 31165 | 203 |
| ... 2B It Alpaca Cleaned SFT 1024 | 8K / 5.2 GB | 116 | 0 |
| Gemma2b Nirf Lookup 2025 | 8K / 5.2 GB | 17 | 0 |
| Gemma2Slerp2 2.6B | 8K / 5.3 GB | 3 | 2 |
| ...emma 2 2B It Chinese Kyara DPO | 8K / 15.7 GB | 1768 | 14 |
Note: green Score (e.g. "73.2") means that the model is better than vectorzhou/gemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-OnlineIPO1-0907045617-epoch-3 .
Rank the Gemma 2 2B It Alpaca Cleaned SFT PKU SafeRLHF OnlineIPO1 0907045617 Epoch 3 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? 51534 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124