bluuwhale/L3-SthenoMaidBlackroot-8B-V1
Full fine-tune vs Hastagaras/Jamet-8B-L3-MK.V-Blackroot. 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
6 derivatives checked
- QuantFactory/L3-SthenoMaidBlackroot-8B-V1-GGUF: Quantization
- mradermacher/L3-SthenoMaidBlackroot-8B-V1-GGUF: Same weights, converted
- mradermacher/L3-SthenoMaidBlackroot-8B-V1-i1-GGUF: Quantization
- featherless-ai-quants/bluuwhale-L3-SthenoMaidBlackroot-8B-V1-GGUF: Quantization
- QuantFactory/L3-SthenoMaid-8B-V1-GGUF: Full fine-tune
- Tremontaine/L3-SthenoMaidBlackroot-15B: Partial fine-tune (fewer layers)