speechless-codellama-34b-v2.0-GGUF

Home/Models/TheBloke/speechless-codellama-34b-v2.0-GGUF

TheBloke/speechless-codellama-34b-v2.0-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: text-generation
root model: uukuguy/speechless-codellama-34b-v2.0
provider: TheBloke
license: llama2
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 342
likes: 10
created: —
last modified: 2023-10-13T11:00:40+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF
tags: transformersggufllamallama-2codetext-generationendataset:jondurbin/airoboros-2.2dataset:Open-Orca/OpenOrcadataset:garage-bAInd/Open-Platypusdataset:WizardLM/WizardLM_evol_instruct_V2_196karxiv:2308.12950base_model:uukuguy/speechless-codellama-34b-v2.0base_model:quantized:uukuguy/speechless-codellama-34b-v2.0license:llama2model-indexregion:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	75.65	HellaSwag	medium	`\| HellaSwag \| 75.65 \|`
HumanEval	coding	75.61	-python	medium	`\| humaneval-python \| 75.61 \|`
MMLU	knowledge	54.67	MMLU	medium	`\| MMLU \| 54.67 \|`
TruthfulQA	safety	45.21	TruthfulQA	medium	`\| TruthfulQA \| 45.21 \|`

none scraped.