speakleash/Bielik-11B-v2.1-Instruct
Full fine-tune vs speakleash/Bielik-11B-v2. Fine-tune: 100% of the weights changed, across 50 of 50 layers.
Tensors changed: Embeddings 1/1, Norms 51/101, MLP 150/150, Attention 200/200, lm_head 1/1
4 derivatives checked
- speakleash/Bielik-11B-v2.1-Instruct-GGUF-IQ-Imatrix: Quantization
- mradermacher/Bielik-11B-v2.1-Instruct-i1-GGUF: Quantization
- speakleash/Bielik-11B-v2.1-Instruct-GGUF: Quantization
- mradermacher/Bielik-11B-v2.1-Instruct-GGUF: Quantization