Entropicengine/LatentDream-exp-alpha-8b
Full fine-tune vs DreadPoor/Aspire-8B-model_stock. 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
3 derivatives checked
- mradermacher/LatentDream-exp-alpha-8b-i1-GGUF: Quantization
- mradermacher/LatentDream-exp-alpha-8b-GGUF: Same weights, converted
- Entropicengine/LatentSoup-modelstock-8b: Full fine-tune