Nanite-Labs/nanites-medieval-e2b-chat
LoRA-style (fewer layers) vs unsloth/gemma-4-E2B-it. Nanite-Labs/nanites-medieval-e2b-chat matches part of unsloth/gemma-4-E2B-it (600 of its 2011 tensors; the rest of unsloth/gemma-4-E2B-it has no counterpart). On the shared part: Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 35 of 35 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/247, other 0/106, MLP 105/105, Attention 140/140
2 derivatives checked
- mradermacher/nanites-medieval-e2b-chat-i1-GGUF: Quantization
- mradermacher/nanites-medieval-e2b-chat-GGUF: Same weights, converted