Hermes-3-Llama-3.1-70B-lorablated

Home/Models/mlabonne/Hermes-3-Llama-3.1-70B-lorablated

mlabonne/Hermes-3-Llama-3.1-70B-lorablated

kind: lora
quant: lora
family: llama
modality: text-generation
root model: NousResearch/Hermes-3-Llama-3.1-70B
provider: mlabonne
license: —
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 246
likes: 38
created: —
last modified: 2024-10-16T13:37:22+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-70B-lorablated
tags: transformerssafetensorsllamatext-generationmergekitmergeconversationalarxiv:2212.04089base_model:NousResearch/Hermes-3-Llama-3.1-70Bbase_model:merge:NousResearch/Hermes-3-Llama-3.1-70Bbase_model:mlabonne/Llama-3-70B-Instruct-abliterated-LORAbase_model:merge:mlabonne/Llama-3-70B-Instruct-abliterated-LORAmodel-indextext-generation-inferenceendpoints_compatibledeploy:azureregion:us

benchmark	category	score	context	conf	evidence
IFEval	instruction-following	71.44	IFEval (0-Shot)	medium	`\| IFEval (0-Shot) \| 71.44 \|`
BBH	reasoning	52.34	BBH (3-Shot)	medium	`\| BBH (3-Shot) \| 52.34 \|`
MMLU-Pro	knowledge	41.37	MMLU-PRO (5-shot)	medium	`\| MMLU-PRO (5-shot) \| 41.37 \|`
MUSR	reasoning	22.02	MuSR (0-shot)	medium	`\| MuSR (0-shot) \| 22.02 \|`
MATH	math	13.82	MATH Lvl 5 (4-Shot)	medium	`\| MATH Lvl 5 (4-Shot) \| 13.82 \|`
GPQA	reasoning	13.2	GPQA (0-shot)	medium	`\| GPQA (0-shot) \| 13.20 \|`

none scraped.