schneewolflabs/B2-9B
LoRA-style vs schneewolflabs/B0-9B. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/1, Norms 0/221, MLP 96/211, Attention 32/336, Embeddings 0/5, lm_head 0/1
3 derivatives checked
- mradermacher/B2-9B-i1-GGUF: Quantization
- mradermacher/B2-9B-GGUF: Same weights, converted
- schneewolflabs/B2-9B-GGUF: Quantization