decapoda-research/Antares-11b-v1
LoRA-style vs upstage/SOLAR-10.7B-Instruct-v1.0. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/192, lm_head 0/1
3 derivatives checked
- mradermacher/Antares-11b-v1-i1-GGUF: Quantization
- mradermacher/Antares-11b-v1-GGUF: Same weights, converted
- featherless-ai-quants/decapoda-research-Antares-11b-v1-GGUF: Quantization