Granite-20B-Code-Instruct
ExLlamav2 8 bpw quants of https://huggingface.co/ibm-granite/granite-20b-code-instruct
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.
Model tree for altomek/Granite-20B-Code-Instruct-8bpw-EXL2
Base model
ibm-granite/granite-20b-code-base-8k
Finetuned
ibm-granite/granite-20b-code-instruct-8k
Datasets used to train altomek/Granite-20B-Code-Instruct-8bpw-EXL2
Evaluation results
- pass@1 on HumanEvalSynthesis(Python)self-reported60.400
- pass@1 on HumanEvalSynthesis(JavaScript)self-reported53.700
- pass@1 on HumanEvalSynthesis(Java)self-reported58.500
- pass@1 on HumanEvalSynthesis(Go)self-reported42.100
- pass@1 on HumanEvalSynthesis(C++)self-reported45.700
- pass@1 on HumanEvalSynthesis(Rust)self-reported42.700
- pass@1 on HumanEvalExplain(Python)self-reported44.500
- pass@1 on HumanEvalExplain(JavaScript)self-reported42.700
- pass@1 on HumanEvalExplain(Java)self-reported49.400
- pass@1 on HumanEvalExplain(Go)self-reported32.300