dranger003/starcoder2-15b-instruct-iMat.GGUF

NOTE: You will need a recent build of llama.cpp to run these quants (i.e. at least commit 494c870).

GGUF importance matrix (imatrix) quants for https://huggingface.co/TechxGenus/starcoder2-15b-instruct

• The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
• The imatrix is being used on the K-quants as well.

Fine-tuned starcoder2-15b with an additional 0.7 billion high-quality, code-related tokens for 3 epochs. We used DeepSpeed ZeRO 3 and Flash Attention 2 to accelerate the training process. It achieves 77.4 pass@1 on HumanEval-Python. This model operates using the Alpaca instruction format (excluding the system prompt).

Layers	Context	Template
40	16384	### Instruction {instruction} ### Response {response}