ChimeraLlama-3-8B-v3

Home/Models/mlabonne/ChimeraLlama-3-8B-v3

mlabonne/ChimeraLlama-3-8B-v3

kind: merge
quant: merge
family: llama
modality: text-generation
root model: NousResearch/Meta-Llama-3-8B-Instruct
provider: mlabonne
license: other
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 8,029
likes: 15
created: —
last modified: 2024-09-17T10:16:45+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v3
tags: transformerssafetensorsllamatext-generationmergemergekitlazymergekitbase_model:Danielbrdz/Barcenas-Llama3-8b-ORPObase_model:merge:Danielbrdz/Barcenas-Llama3-8b-ORPObase_model:MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3base_model:merge:MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3base_model:NousResearch/Meta-Llama-3-8B-Instructbase_model:merge:NousResearch/Meta-Llama-3-8B-Instructbase_model:VAGOsolutions/Llama-3-SauerkrautLM-8b-Instructbase_model:merge:VAGOsolutions/Llama-3-SauerkrautLM-8b-Instructbase_model:dphn/dolphin-2.9-llama3-8bbase_model:merge:dphn/dolphin-2.9-llama3-8bbase_model:mlabonne/OrpoLlama-3-8Bbase_model:merge:mlabonne/OrpoLlama-3-8Bbase_model:vicgalle/Configurable-Llama-3-8B-v0.3base_model:merge:vicgalle/Configurable-Llama-3-8B-v0.3license:othermodel-indextext-generation-inference

benchmark	category	score	context	conf	evidence
IFEval	instruction-following	44.08	IFEval (0-Shot)	medium	`\| IFEval (0-Shot) \| 44.08 \|`
MMLU-Pro	knowledge	29.65	MMLU-PRO (5-shot)	medium	`\| MMLU-PRO (5-shot) \| 29.65 \|`
BBH	reasoning	27.65	BBH (3-Shot)	medium	`\| BBH (3-Shot) \| 27.65 \|`
MUSR	reasoning	8.38	MuSR (0-shot)	medium	`\| MuSR (0-shot) \| 8.38 \|`
MATH	math	7.85	MATH Lvl 5 (4-Shot)	medium	`\| MATH Lvl 5 (4-Shot) \| 7.85 \|`
GPQA	reasoning	5.59	GPQA (0-shot)	medium	`\| GPQA (0-shot) \| 5.59 \|`

none scraped.