Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Q-bert_-_MetaMath-Cybertron-Starling-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
Q-bert_-_MetaMath-Cybertron-Starling-gguf
like
0
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
MetaMath-Cybertron-Starling - GGUF
Model creator:
https://huggingface.co/Q-bert/
Original model:
https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling/
Name
Quant method
Size
MetaMath-Cybertron-Starling.Q2_K.gguf
Q2_K
2.53GB
MetaMath-Cybertron-Starling.IQ3_XS.gguf
IQ3_XS
2.81GB
MetaMath-Cybertron-Starling.IQ3_S.gguf
IQ3_S
2.96GB
MetaMath-Cybertron-Starling.Q3_K_S.gguf
Q3_K_S
2.95GB
MetaMath-Cybertron-Starling.IQ3_M.gguf
IQ3_M
3.06GB
MetaMath-Cybertron-Starling.Q3_K.gguf
Q3_K
3.28GB
MetaMath-Cybertron-Starling.Q3_K_M.gguf
Q3_K_M
3.28GB
MetaMath-Cybertron-Starling.Q3_K_L.gguf
Q3_K_L
3.56GB
MetaMath-Cybertron-Starling.IQ4_XS.gguf
IQ4_XS
3.67GB
MetaMath-Cybertron-Starling.Q4_0.gguf
Q4_0
3.83GB
MetaMath-Cybertron-Starling.IQ4_NL.gguf
IQ4_NL
3.87GB
MetaMath-Cybertron-Starling.Q4_K_S.gguf
Q4_K_S
3.86GB
MetaMath-Cybertron-Starling.Q4_K.gguf
Q4_K
4.07GB
MetaMath-Cybertron-Starling.Q4_K_M.gguf
Q4_K_M
4.07GB
MetaMath-Cybertron-Starling.Q4_1.gguf
Q4_1
4.24GB
MetaMath-Cybertron-Starling.Q5_0.gguf
Q5_0
4.65GB
MetaMath-Cybertron-Starling.Q5_K_S.gguf
Q5_K_S
4.65GB
MetaMath-Cybertron-Starling.Q5_K.gguf
Q5_K
4.78GB
MetaMath-Cybertron-Starling.Q5_K_M.gguf
Q5_K_M
4.78GB
MetaMath-Cybertron-Starling.Q5_1.gguf
Q5_1
5.07GB
MetaMath-Cybertron-Starling.Q6_K.gguf
Q6_K
5.53GB
MetaMath-Cybertron-Starling.Q8_0.gguf
Q8_0
6.27GB
Original model description:
license: cc-by-nc-4.0 datasets:
meta-math/MetaMathQA language:
en pipeline_tag: text-generation tags:
Math
merge base_model:
Q-bert/MetaMath-Cybertron
berkeley-nest/Starling-LM-7B-alpha
MetaMath-Cybertron-Starling
Merge
Q-bert/MetaMath-Cybertron
and
berkeley-nest/Starling-LM-7B-alpha
using slerp merge.
You can use ChatML format.
Open LLM Leaderboard Evaluation Results
Detailed results can be found
Here
Metric
Value
Avg.
71.35
ARC (25-shot)
67.75
HellaSwag (10-shot)
86.23
MMLU (5-shot)
65.24
TruthfulQA (0-shot)
55.94
Winogrande (5-shot)
81.45
GSM8K (5-shot)
71.49