bluuwhale/L3-SthenoMaid-8B-V1

Full fine-tune vs NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 35/65, MLP 93/96, Attention 124/128, lm_head 1/1

3 derivatives checked

• bartowski/L3-SthenoMaid-8B-V1-GGUF: Same weights, converted
• mradermacher/L3-SthenoMaid-8B-V1-i1-GGUF: Quantization
• mradermacher/L3-SthenoMaid-8B-V1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse