nkpz/OpenThinker-7B-Uncensored-DeLMAT
LoRA-style vs open-thoughts/OpenThinker-7B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 55/84, Attention 0/196, lm_head 0/1
2 derivatives checked
- mradermacher/OpenThinker-7B-Uncensored-DeLMAT-i1-GGUF: Quantization
- mradermacher/OpenThinker-7B-Uncensored-DeLMAT-GGUF: Same weights, converted