muranAI/DeepSeek-R1-0528-Qwen3-8B-GGUF

LoRA-style vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. muranAI/DeepSeek-R1-0528-Qwen3-8B-GGUF is a GGUF (BF16) 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 22 of 36 layers; norms, biases and embeddings are untouched.

Tensors changed: Embeddings 0/1, Attention 12/144, Norms 0/145, MLP 18/108, lm_head 0/1

On the Hub · Downloads on Model Pulse