lynx   »   [go: up one dir, main page]

\"image.png\"

\n

Later, tried using without fp16 precision as -

\n

optimum-cli export onnx --model google/gemma-7b --framework pt --task text-generation-with-past ./gemma-7b

\n

And successfully got the onnx file in INT64 precision.
Now when I try to convert it to FP16/INT4 it is thowing an error as -

\n

\"Screenshot

\n

Any clues on what to do about this?

\n","updatedAt":"2024-04-24T12:06:48.351Z","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5449169278144836},"editors":["Avan2000"],"editorAvatarUrls":["/avatars/60d013f95b6cd5326e5ca85b0873368f.svg"],"reactions":[],"isReport":false}},{"id":"6630b25ab6cca78994939a9b","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isOwner":false,"isOrgMember":false},"createdAt":"2024-04-30T08:56:58.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hi Community, Any update on this ?","html":"

Hi Community, Any update on this ?

\n","updatedAt":"2024-04-30T08:56:58.727Z","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7172293066978455},"editors":["Avan2000"],"editorAvatarUrls":["/avatars/60d013f95b6cd5326e5ca85b0873368f.svg"],"reactions":[],"isReport":false}}],"pinned":false,"locked":false,"collection":"discussions","isPullRequest":false,"isReport":false},"repo":{"name":"google/gemma-7b","type":"model"},"activeTab":"discussion","discussionRole":0,"watched":false,"muted":false,"repoDiscussionsLocked":false}">

Unable to convert ONNX model to INT4/FP16

#95
by Avan2000 - opened
\"image.png\"

\n

Later, tried using without fp16 precision as -

\n

optimum-cli export onnx --model google/gemma-7b --framework pt --task text-generation-with-past ./gemma-7b

\n

And successfully got the onnx file in INT64 precision.
Now when I try to convert it to FP16/INT4 it is thowing an error as -

\n

\"Screenshot

\n

Any clues on what to do about this?

\n","updatedAt":"2024-04-24T12:06:48.351Z","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5449169278144836},"editors":["Avan2000"],"editorAvatarUrls":["/avatars/60d013f95b6cd5326e5ca85b0873368f.svg"],"reactions":[],"isReport":false}},{"id":"6630b25ab6cca78994939a9b","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isOwner":false,"isOrgMember":false},"createdAt":"2024-04-30T08:56:58.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hi Community, Any update on this ?","html":"

Hi Community, Any update on this ?

\n","updatedAt":"2024-04-30T08:56:58.727Z","author":{"_id":"65f816123a8814cf2f796770","avatarUrl":"/avatars/60d013f95b6cd5326e5ca85b0873368f.svg","fullname":"Navadeep Komarraju","name":"Avan2000","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7172293066978455},"editors":["Avan2000"],"editorAvatarUrls":["/avatars/60d013f95b6cd5326e5ca85b0873368f.svg"],"reactions":[],"isReport":false}}],"pinned":false,"locked":false,"collection":"discussions","isPullRequest":false,"isReport":false},"primaryEmailConfirmed":false,"repo":{"name":"google/gemma-7b","type":"model"},"discussionRole":0,"acceptLanguages":["*"],"hideComments":true,"repoDiscussionsLocked":false,"isDiscussionAuthor":false}">

Hi community,

I tried converting the Gemma-7b model to onnx file with fp16 precision using the following command -

optimum-cli export onnx --dtype fp16 --device xpu --model google/gemma-7b --framework pt --task text-generation-with-past ./gemma-7b

But it is giving an error like -

image.png

Later, tried using without fp16 precision as -

optimum-cli export onnx --model google/gemma-7b --framework pt --task text-generation-with-past ./gemma-7b

And successfully got the onnx file in INT64 precision.
Now when I try to convert it to FP16/INT4 it is thowing an error as -

Screenshot 2024-04-24 155241.png

Any clues on what to do about this?

Hi Community, Any update on this ?

Sign up or log in to comment

Лучший частный хостинг