upstage/SOLAR-10.7B-Instruct-v1.0
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
13 derivatives checked
- TheBloke/SOLAR-10.7B-Instruct-v1.0-AWQ: Quantization
- TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF: Quantization
- mradermacher/SOLAR-10.7B-Instruct-v1.0-GGUF: Same weights, converted
- mradermacher/SOLAR-10.7B-Instruct-v1.0-i1-GGUF: Quantization
- second-state/SOLAR-10.7B-Instruct-v1.0-GGUF: Quantization
- vicgalle/SOLAR-13B-Instruct-v1.0: Partial fine-tune
- featherless-ai-quants/upstage-SOLAR-10.7B-Instruct-v1.0-GGUF: Quantization
- fblgit/UNA-SOLAR-10.7B-Instruct-v1.0: Full fine-tune
- naver/pisco-solar: Adapter
- dhanushreddy29/BrokenKeyboard: LoRA-style
- megastudyedu/M-SOLAR-10.7B-v1.1-beta: LoRA-style
- decapoda-research/Antares-11b-v1: LoRA-style
- jjourney1125/M-SOLAR-10.7B-v1.0: LoRA-style
5 other repos hold byte-for-byte identical weight files.