MaziyarPanahi/Llama-3-8B-Instruct-v0.3

Full fine-tune vs MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 93/96, Attention 124/128, lm_head 1/1

3 derivatives checked

• mradermacher/Llama-3-8B-Instruct-v0.3-i1-GGUF: Quantization
• MaziyarPanahi/Llama-3-8B-Instruct-v0.3-GGUF: Quantization
• mradermacher/Llama-3-8B-Instruct-v0.3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse