Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
LoRA-style vs google/gemma-7b. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/112
4 derivatives checked
- mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF: Quantization
- mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-GGUF: Same weights, converted
- tensorblock/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-GGUF: Quantization
- saucam/Navrasa-2.0-Rudra-7b-dare-ties: LoRA-style