WoonaAI/OmniLing-V1-8b-experimental
Partial fine-tune vs AnatoliiPotapov/T-lite-instruct-0.1. Partial change: 77% of the weights changed (attention, embeddings, mlp), in 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 78/96, Attention 101/128, lm_head 0/1
2 derivatives checked
- mradermacher/OmniLing-V1-8b-experimental-i1-GGUF: Quantization
- mradermacher/OmniLing-V1-8b-experimental-GGUF: Same weights, converted