sarvamai/sarvam-m
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Base-2503. sarvamai/sarvam-m matches part of mistralai/Mistral-Small-3.1-24B-Base-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Base-2503 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 79/81, MLP 120/120, Attention 160/160, lm_head 1/1
6 derivatives checked
- bartowski/sarvamai_sarvam-m-GGUF: Same weights, converted
- sarvamai/sarvam-m-q8-gguf: Quantization
- lmstudio-community/sarvam-m-GGUF: Quantization
- DevQuasar/sarvamai.sarvam-m-GGUF: Same weights, converted
- smarttasks/sarvam-m-GGUF: Quantization
- shiva123782/Kaveri-AI-3DNet: Adapter
5 other repos hold byte-for-byte identical weight files.