google/gemma-2-2b-it
Full fine-tune vs google/gemma-2-2b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 105/105, MLP 78/78, Attention 104/104
90 derivatives checked
- MaziyarPanahi/gemma-2-2b-it-GGUF: Same weights, converted
- bartowski/gemma-2-2b-it-GGUF: Quantization
- google/gemma-2-2b-jpn-it: Full fine-tune
- lemuralabs/Gemma-2B-Uncensored-GGUF: Not comparable yet
- lmstudio-community/gemma-2-2b-it-GGUF: Quantization
- KolmogorovAcc/sovereign-anthology-gemma-2-2b: LoRA-style
- legraphista/gemma-2-2b-it-IMat-GGUF: Same weights, converted
- anakin87/gemma-2-2b-neogenesis-ita: Partial fine-tune
- QuantFactory/Gemma-2-2b-Chinese-it-GGUF: Full fine-tune
- QuantFactory/Gemma-2-2B-Stheno-Filtered-GGUF: Full fine-tune
- QuantFactory/Atlas-Chat-2B-GGUF: Full fine-tune
- mradermacher/gemma-2-2b-it-GGUF: Same weights, converted
- QuantFactory/Vikhr-Gemma-2B-instruct-GGUF: Full fine-tune
- mradermacher/gemma-2-2b-it-i1-GGUF: Quantization
- second-state/gemma-2-2b-it-GGUF: Same weights, converted
- ElementMerc/gemma-2-2b-it-abliterated: Abliterated
- Mykes/medicus: LoRA-style
- thoughtworks/backdoor-gemma2-2b-2pair-french: Full fine-tune
- thoughtworks/backdoor-gemma2-2b-2single-french: Full fine-tune
- BafS/gemma-2-2b-it-Q4_K_M-GGUF: Quantization
- thoughtworks/backdoor-gemma2-2b-4single-french: Full fine-tune
- thoughtworks/backdoor-gemma2-2b-4pair-french: Full fine-tune
- QuantFactory/gemma-2-2b-jpn-it-GGUF: Full fine-tune
- QuantFactory/Meditron3-Gemma2-2B-GGUF: Full fine-tune
- zake7749/gemma-2-2b-it-chinese-kyara-dpo: Full fine-tune
- featherless-ai-quants/google-gemma-2-2b-it-GGUF: Quantization
- Vikhrmodels/Vikhr-Gemma-2B-instruct: LoRA-style
- tensorblock/gemma-2-2b-it-GGUF: Quantization
- gaianet/gemma-2-2b-it-GGUF: Same weights, converted
- EYEDOL/adtc-agri-sft-gemma2-2b: LoRA-style
25 other repos hold byte-for-byte identical weight files.