bigcode/starcoder2-15b-instruct-v0.1
Full fine-tune vs bigcode/starcoder2-15b. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 97/162, MLP 160/160, Attention 320/320, lm_head 1/1
5 derivatives checked
- mradermacher/starcoder2-15b-instruct-v0.1-GGUF: Quantization
- QuantFactory/starcoder2-15b-instruct-v0.1-GGUF: Quantization
- second-state/StarCoder2-15B-Instruct-v0.1-GGUF: Same weights, converted
- gaianet/StarCoder2-15B-Instruct-v0.1-GGUF: Same weights, converted
- DevQuasar-9/bigcode.starcoder2-15b-instruct-v0.1-GGUF: Same weights, converted