llemma_34b-GGUF

Home/Models/TheBloke/llemma_34b-GGUF

TheBloke/llemma_34b-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: EleutherAI/llemma_34b
provider: TheBloke
license: llama2
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 320
likes: 10
created: —
last modified: 2023-10-17T21:41:45+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/llemma_34b-GGUF
tags: transformersggufllamamathreasoningendataset:EleutherAI/proof-pile-2arxiv:2310.10631base_model:EleutherAI/llemma_34bbase_model:quantized:EleutherAI/llemma_34blicense:llama2region:us

benchmark	category	score	conf	evidence
MMLU	knowledge	37.7	high	`\| LLEMMA \| 7B \| 36.4% \| 7.7% \| 37.7% \| 53.1% \| 18.0% \|`
GSM8K	math	36.4	high	`\| LLEMMA \| 7B \| 36.4% \| 7.7% \| 37.7% \| 53.1% \| 18.0% \|`
MATH	math	18.0	high	`\| LLEMMA \| 7B \| 36.4% \| 7.7% \| 37.7% \| 53.1% \| 18.0% \|`

none scraped.