WizardCoder-33B-V1.1-GGUF

Home/Models/TheBloke/WizardCoder-33B-V1.1-GGUF

TheBloke/WizardCoder-33B-V1.1-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: WizardLM/WizardCoder-33B-V1.1
provider: TheBloke
license: —
language: —
context: 16384,
library: transformers
vRAM (GB): —
size on disk: —
downloads: 321
likes: 45
created: —
last modified: 2024-01-04T17:36:00+00:00 (2024)
huggingface: https://huggingface.co/TheBloke/WizardCoder-33B-V1.1-GGUF
tags: transformersggufdeepseekcodearxiv:2304.12244arxiv:2306.08568arxiv:2308.09583base_model:WizardLMTeam/WizardCoder-33B-V1.1base_model:quantized:WizardLMTeam/WizardCoder-33B-V1.1model-indexregion:us

benchmark	category	score	context	conf	evidence
HumanEval	coding	85.4		low	`\| GPT-4-Turbo (Nov 2023) \| - \| - \| 85.4 \| 81.7 \| 83.0 \| 70.7 \| - \|`
MBPP	coding	83.0		low	`\| GPT-4-Turbo (Nov 2023) \| - \| - \| 85.4 \| 81.7 \| 83.0 \| 70.7 \| - \|`

none scraped.