Tesslate/Tessa-T1-3B
LoRA-style vs Qwen/Qwen2.5-Coder-3B-Instruct. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/252
4 derivatives checked
- bartowski/Tesslate_Tessa-T1-3B-GGUF: Same weights, converted
- second-state/Tessa-T1-3B-GGUF: Same weights, converted
- gaianet/Tessa-T1-3B-GGUF: Same weights, converted
- mradermacher/Tessa-T1-3B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.