SicariusSicariiStuff/Impish_Mind_8B
Full fine-tune vs ruliad/deepthought-8b-llama-v0.01-alpha. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 25/65, MLP 96/96, Attention 128/128, lm_head 1/1
7 derivatives checked
- bartowski/Impish_Mind_8B-GGUF: Same weights, converted
- mradermacher/Impish_Mind_8B-i1-GGUF: Quantization
- SicariusSicariiStuff/Impish_Mind_8B_GGUF: Quantization
- SicariusSicariiStuff/Impish_Mind_8B_iMatrix: Quantization
- mradermacher/Impish_Mind_8B-GGUF: Same weights, converted
- SicariusSicariiStuff/Impish_Mind_8B_GGUF_HA: Quantization
- mergekit-community/R1-ImpishMind-8B: Full fine-tune