Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B-MTP-GGUF

LoRA-style vs unsloth/Qwen3.5-4B. Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B-MTP-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 32 of 32 layers; norms, biases and embeddings are untouched.

Tensors changed: Embeddings 0/1, MLP 96/96, Norms 0/81, Attention 32/32

On the Hub · Downloads on Model Pulse