internlm/OREAL-7B

Full fine-tune vs internlm/OREAL-7B-SFT. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

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

4 derivatives checked

• bartowski/internlm_OREAL-7B-GGUF: Quantization
• mradermacher/OREAL-7B-i1-GGUF: Quantization
• mradermacher/OREAL-7B-GGUF: Same weights, converted
• DevQuasar-7/internlm.OREAL-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse