rlhf-and-friends/TLDR-Qwen2-0.5B-SmallSFT
LoRA-style vs Qwen/Qwen2-0.5B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 96/168
1 derivatives checked
- mradermacher/SFT-TLDR-Qwen2-0.5B-SMALL-GGUF: Same weights, converted