Rockinsince87/L3-8B-EnchantedForest-v0.5

Full fine-tune vs Dampfinchen/Llama-3-8B-Ultra-Instruct. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 64/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/L3-8B-EnchantedForest-v0.5-i1-GGUF: Quantization
• mradermacher/L3-8B-EnchantedForest-v0.5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse