CallComply/SOLAR-10.7B-Instruct-v1.0-128k
Full fine-tune vs upstage/SOLAR-10.7B-v1.0. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 192/192, lm_head 1/1
5 derivatives checked
- cgus/SOLAR-10.7B-Instruct-v1.0-128k-iMat-GGUF: Same weights, converted
- cgus/SOLAR-10.7B-Instruct-v1.0-128k-GGUF: Same weights, converted
- mradermacher/SOLAR-10.7B-Instruct-v1.0-128k-i1-GGUF: Quantization
- featherless-ai-quants/CallComply-SOLAR-10.7B-Instruct-v1.0-128k-GGUF: Quantization
- mradermacher/SOLAR-10.7B-Instruct-v1.0-128k-GGUF: Same weights, converted
5 other repos hold byte-for-byte identical weight files.