GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
Full fine-tune vs GoToCompany/gemma2-9b-cpt-sahabatai-v1-base. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 169/169, MLP 126/126, Attention 168/168
7 derivatives checked
- mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-i1-GGUF: Quantization
- gmonsoon/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF: Same weights, converted
- mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF: Same weights, converted
- gmonsoon/SahabatAI-Lion-9B-TIES-v1-GGUF: Full fine-tune
- farwew/gemma2-9b-cpt-sahabatai-v1-instruct-Med_QA_LoRA: Full fine-tune
- mlx-community/gemma2-9b-cpt-sahabatai-v1-instruct-4bit: Quantization
- gmonsoon/SahabatAI-Lion-9B-TIES-v1: Full fine-tune
1 other repos hold byte-for-byte identical weight files.