jsfs11/L3-8b-SthenoLumiM-ModelStock

Full fine-tune vs NeverSleep/Llama-3-Lumimaid-8B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 32/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/L3-8b-SthenoLumiM-ModelStock-i1-GGUF: Quantization
• mradermacher/L3-8b-SthenoLumiM-ModelStock-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse