NexesQuants
/

hitachi-nlp_Llama-3.1-70B-FLDx2-iMat-CQ-GGUF

Model card Files Files and versions

about

This model has the lowest perplexity I know so far for a finetuned Llama 3.1 base : 2.83 (Wikitext Eng 512) ; 4.00 (Wikitext FR 512)

Arc-C : around 60
Arc-E : around 80

Downloads last month: 3

GGUF

Model size

70.6B params

Architecture

llama

Hardware compatibility

Log In to view the estimation

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NexesQuants/hitachi-nlp_Llama-3.1-70B-FLDx2-iMat-CQ-GGUF

Base model

hitachi-nlp/Llama-3.1-70B-FLDx2

Quantized

(3)

this model