Edentns/DataVortexS-10.7B-v1.0
LoRA-style vs megastudyedu/M-SOLAR-10.7B-v1.3. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of gate_proj, k_proj, o_proj, q_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 48/144, Attention 192/192, lm_head 0/1
2 derivatives checked
- mradermacher/DataVortexS-10.7B-v1.0-i1-GGUF: Quantization
- featherless-ai-quants/Edentns-DataVortexS-10.7B-v1.0-GGUF: Quantization