Tesslate/Tessa-T1-14B
LoRA-style vs Qwen/Qwen2.5-Coder-14B-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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/336, lm_head 0/1
4 derivatives checked
- bartowski/Tesslate_Tessa-T1-14B-GGUF: Same weights, converted
- second-state/Tessa-T1-14B-GGUF: Same weights, converted
- mradermacher/Tessa-T1-14B-GGUF: Quantization
- gaianet/Tessa-T1-14B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.