eas/
omnibeagle:q8_0

51 1 year ago

Omnibeagel with 4K context

1 year ago

73b2fb8bdf37 · 7.7GB ·

model
llama
·
7.24B
·
Q8_0
params
{ "num_ctx": 4096, "stop": [ "<|im_end|>", "|im_end|>", "<|im_start|
template
<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

Readme

From mlabonne/OmniBeagle-7B

OmniBeagle-7B is a merge of the following models using LazyMergekit:

shadowml/BeagleSempra-7B shadowml/BeagSake-7B shadowml/WestBeagle-7B