GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
Full fine-tune vs GoToCompany/llama3-8b-cpt-sahabatai-v1-base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 14/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- gmonsoon/llama3-8b-cpt-sahabatai-v1-instruct-GGUF: Same weights, converted
- Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf: Quantization
- mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF: Same weights, converted
- gmonsoon/SahabatAI-MediChatIndo-8B-v1: Full fine-tune
- gmonsoon/Eunoia-Llama-8B-R1: Full fine-tune
- gmonsoon/EunoiaHermes-3-Llama-3-8B-Preview: Full fine-tune
2 other repos hold byte-for-byte identical weight files.