dataslab/DSLM-LST-9B
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 11% of the weights changed (lm_head), in 0 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/5, MLP 0/211, Attention 0/336, other 0/1, Norms 0/221
4 derivatives checked
- mradermacher/DLM-LST-9B-GGUF: Same weights, converted
- mradermacher/DSLM-LST-9B-i1-GGUF: Quantization
- mradermacher/DLM-LST-9B-i1-GGUF: Quantization
- mradermacher/DSLM-LST-9B-GGUF: Same weights, converted