sethuiyer/SynthIQ-7b

Full fine-tune vs HuggingFaceH4/zephyr-7b-alpha. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/SynthIQ-7b-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse