HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Starling-LM-7B-alpha-AWQ

TheBloke/Starling-LM-7B-alpha-AWQ

kind
awq
quant
awq
family
misc
modality
text-generation
root model
berkeley-nest/Starling-LM-7B-alpha
provider
TheBloke
license
cc-by-nc-4.0
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
107
likes
9
created
—
last modified
2023-11-28T16:06:57+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Starling-LM-7B-alpha-AWQ
tags
transformerssafetensorsmistraltext-generationreward modelRLHFRLAIFconversationalendataset:berkeley-nest/Nectararxiv:2306.02231base_model:berkeley-nest/Starling-LM-7B-alphabase_model:quantized:berkeley-nest/Starling-LM-7B-alphalicense:cc-by-nc-4.0text-generation-inference4-bitawqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
AlpacaEvalchat97.7low| GPT-4-Turbo | ? | 9.32 | 97.70 | |
MMLUknowledge86.4low| GPT-4 | SFT + PPO | 8.99 | 95.28 | 86.4 |
MT-Benchchat9.32low| GPT-4-Turbo | ? | 9.32 | 97.70 | |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.