LLM-OS-Models/Fabliq-8B-Agent-FromBase-Reasoning

Full fine-tune vs LLM-OS-Models/Fabliq-8B-Agent-FromBase. Fine-tune: 93% of the weights changed, across 24 of 24 layers.

Tensors changed: MLP 2041/2162, Embeddings 0/2, other 54/54, Norms 8/60, Attention 24/24

2 derivatives checked

• mradermacher/Fabliq-8B-Agent-FromBase-Reasoning-i1-GGUF: Quantization
• mradermacher/Fabliq-8B-Agent-FromBase-Reasoning-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse