Salesforce/E1-Math-7B

Partial fine-tune vs Skywork/Skywork-OR1-Math-7B. Partial change: 86% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 38/57, MLP 84/84, Attention 195/196, lm_head 0/1

3 derivatives checked

• mradermacher/E1-Math-7B-i1-GGUF: Quantization
• mradermacher/E1-Math-7B-GGUF: Same weights, converted
• DevQuasar/Salesforce.E1-Math-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse