attn-signs/GPTR-8b-v1

Full fine-tune vs attn-signs/GPTR-8b-base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 31/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/GPTR-8-v1-i1-GGUF: Quantization
• mradermacher/GPTR-8-v1-GGUF: Same weights, converted
• attn-signs/GPTR-8b-v2: LoRA-style

On the Hub · Downloads on Model Pulse