mradermacher/SuperCoder-7B-Qwen2.5-0525-peft-grpo-v2-merged-GGUF
LoRA-style vs ferdinandjasong/SuperCoder-7B-Qwen2.5-0525-peft-grpo-v2-merged. mradermacher/SuperCoder-7B-Qwen2.5-0525-peft-grpo-v2-merged-GGUF is a GGUF (F16) of different weights. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 83/84, Attention 112/196, lm_head 0/1