GoToCompany/llama3-8b-cpt-sahabatai-v1-base
Full fine-tune vs aisingapore/Llama-SEA-LION-v2-8B-IT. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/llama3-8b-cpt-sahabatai-v1-base-GGUF: Same weights, converted
- GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct: Full fine-tune
- akahana/indo-psikologi-8b: LoRA-style
1 other repos hold byte-for-byte identical weight files.