OpenLLM-Ro/RoLlama2-7b-Instruct

Full fine-tune vs OpenLLM-Ro/RoLlama2-7b-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• legraphista/RoLlama2-7b-Instruct-IMat-GGUF: Full fine-tune
• legraphista/RoLlama2-7b-Instruct-GGUF: Full fine-tune
• mradermacher/RoLlama2-7b-Instruct-GGUF: Full fine-tune

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse