Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
Full fine-tune vs Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
8 derivatives checked
- mradermacher/L3-Umbral-Mind-RP-v1.0-8B-i1-GGUF: Quantization
- QuantFactory/L3-Umbral-Mind-RP-v1.0-8B-GGUF: Quantization
- mradermacher/L3-Umbral-Mind-RP-v1.0-8B-GGUF: Same weights, converted
- mpasila/Llama-3-Umbral-Mind-Replete-8B: Full fine-tune
- mpasila/Llama-3-Umbral-Mind-SimPO-8B: Full fine-tune
- mpasila/Llama-3-Umbral-Mind-Instruct-8B: Full fine-tune
- Tremontaine/Llama3-Omphalos-12B: Full fine-tune (fewer layers)
- Tremontaine/L3-Umbral-Mind-RP-v1.0-15B: Partial fine-tune (fewer layers)