cogvlm2-llama3-chat-19B

Home/Models/zai-org/cogvlm2-llama3-chat-19B

zai-org/cogvlm2-llama3-chat-19B

kind: original
quant: bf16 (16-bit)
family: llama
modality: text-generation
root model: zai-org/cogvlm2-llama3-chat-19B
provider: zai-org
license: other
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 5,474
likes: 220
created: —
last modified: 2024-09-03T16:38:05+00:00 (2024)
huggingface: https://huggingface.co/zai-org/cogvlm2-llama3-chat-19B
tags: transformerssafetensorstext-generationchatcogvlm2conversationalcustom_codeenarxiv:2408.16500arxiv:2311.03079license:otherregion:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	78.2	Open Source	low	`\| LLaVA-NeXT-LLaMA3 \| ✅ \| 8B \| - \| 78.2 \| 69.5 \| - \| - \| - \| 41.7 \| - \| 72.1 \|`
ChartQA	multimodal	68.3	Open Source	low	`\| CogVLM1.1 \| ✅ \| 7B \| 69.7 \| - \| 68.3 \| 590 \| 73.9 \| 34.6 \| 37.3 \| 52.0 \| 65.8 \|`
MMBench	multimodal	65.8	Open Source	low	`\| CogVLM1.1 \| ✅ \| 7B \| 69.7 \| - \| 68.3 \| 590 \| 73.9 \| 34.6 \| 37.3 \| 52.0 \| 65.8 \|`
MMMU	multimodal	37.3	Open Source	low	`\| CogVLM1.1 \| ✅ \| 7B \| 69.7 \| - \| 68.3 \| 590 \| 73.9 \| 34.6 \| 37.3 \| 52.0 \| 65.8 \|`

none scraped.