Salesforce/E1-AceReason-14B

Partial fine-tune vs nvidia/AceReason-Nemotron-14B. Partial change: 89% of the weights changed (attention, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 91/97, MLP 144/144, Attention 336/336, lm_head 0/1

3 derivatives checked

• mradermacher/E1-AceReason-14B-i1-GGUF: Quantization
• mradermacher/E1-AceReason-14B-GGUF: Quantization
• DevQuasar/Salesforce.E1-AceReason-14B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse