RavichandranJ/Hermes-4-14B-OBLITERATED-V2

Full fine-tune vs NousResearch/Hermes-4-14B. Fine-tune: 90% of the weights changed, across 38 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 114/120, Attention 152/160, lm_head 1/1

3 derivatives checked

• mradermacher/Hermes-4-14B-OBLITERATED-V2-i1-GGUF: Quantization
• mradermacher/Hermes-4-14B-OBLITERATED-V2-GGUF: Quantization
• RavichandranJ/Hermes-4-14B-OBLITERATED-V2-Q4_K_M-GGUF: Quantization

On the Hub · Downloads on Model Pulse