facebook/KernelLLM
Full fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- bartowski/facebook_KernelLLM-GGUF: Same weights, converted
- unsloth/KernelLLM-GGUF: Same weights, converted
- mradermacher/KernelLLM-i1-GGUF: Quantization
- mradermacher/KernelLLM-GGUF: Same weights, converted
- lmstudio-community/KernelLLM-GGUF: Quantization
- DevQuasar/facebook.KernelLLM-GGUF: Same weights, converted