inclusionAI/Ling-Coder-lite

Full fine-tune vs inclusionAI/Ling-Coder-lite-base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Attention 56/56, Norms 57/57, MLP 2884/2884, other 0/1, Embeddings 1/1, lm_head 1/1

4 derivatives checked

• mradermacher/Ling-Coder-lite-i1-GGUF: Quantization
• mradermacher/Ling-Coder-lite-GGUF: Quantization
• DevQuasar-12/inclusionAI.Ling-Coder-lite-GGUF: Partial fine-tune
• redponike/Ling-Coder-lite-GGUF: Quantization

On the Hub · Downloads on Model Pulse