Takenoko12345678/NeoHorse-1-9B-Math-SFT
LoRA-style vs TokenRhythm/NeoHorse-1-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 152/224, MLP 96/96, lm_head 0/1
3 derivatives checked
- mradermacher/NeoHorse-1-9B-Math-SFT-i1-GGUF: Quantization
- mradermacher/NeoHorse-1-9B-Math-SFT-GGUF: Same weights, converted
- Takenoko12345678/NeoHorse-1-9B-Math-SFT-GGUF: Quantization